library(readxl)
library(dplyr)
##
## Attaching package: 'dplyr'
## The following objects are masked from 'package:stats':
##
## filter, lag
## The following objects are masked from 'package:base':
##
## intersect, setdiff, setequal, union
library(devtools)
## Loading required package: usethis
library(tidyverse)
## ── Attaching packages ─────────────────────────────────────── tidyverse 1.3.2
## ──
## ✔ ggplot2 3.4.0 ✔ purrr 1.0.1
## ✔ tibble 3.1.8 ✔ stringr 1.5.0
## ✔ tidyr 1.3.0 ✔ forcats 1.0.0
## ✔ readr 2.1.3
## ── Conflicts ────────────────────────────────────────── tidyverse_conflicts() ──
## ✖ dplyr::filter() masks stats::filter()
## ✖ dplyr::lag() masks stats::lag()
library(ggbiplot)
## Loading required package: plyr
## ------------------------------------------------------------------------------
## You have loaded plyr after dplyr - this is likely to cause problems.
## If you need functions from both plyr and dplyr, please load plyr first, then dplyr:
## library(plyr); library(dplyr)
## ------------------------------------------------------------------------------
##
## Attaching package: 'plyr'
##
## The following object is masked from 'package:purrr':
##
## compact
##
## The following objects are masked from 'package:dplyr':
##
## arrange, count, desc, failwith, id, mutate, rename, summarise,
## summarize
##
## Loading required package: scales
##
## Attaching package: 'scales'
##
## The following object is masked from 'package:purrr':
##
## discard
##
## The following object is masked from 'package:readr':
##
## col_factor
##
## Loading required package: grid
library(ggplot2)
library(GGally)
## Registered S3 method overwritten by 'GGally':
## method from
## +.gg ggplot2
library(mice) # for inputation
##
## Attaching package: 'mice'
##
## The following object is masked from 'package:stats':
##
## filter
##
## The following objects are masked from 'package:base':
##
## cbind, rbind
library(ggmice) # for inputation
##
## Attaching package: 'ggmice'
##
## The following objects are masked from 'package:mice':
##
## bwplot, densityplot, stripplot, xyplot
library(scales)
#install.packages("corrplot")
library(corrplot)
## corrplot 0.92 loaded
library(writexl)
### Importing datasets
df <- read_excel("data_2000.xlsx")
z_score <- function(x){
zscore= ((x - mean(x, na.rm = TRUE))/sd(x, na.rm = TRUE))
zscore
}
df$employees_2001_norm <- z_score(df$employees_2001)
df$air_quality_norm <- z_score(df$air_quality)
df$water_quality_norm <- z_score(df$water_quality)
df$built_quality_norm <- z_score(df$built_quality)
df$land_quality_norm <- z_score(df$land_quality)
df$impervious_surface_norm <- z_score(df$impervious_surface)
##Plotting ## Causality_log and Property Damage log
################### causality plot ################################
causality <- ggplot(df, aes(causality_log))
causality + geom_histogram(binwidth = 0.8) ### left-skewed
################### Crop & Property Damage log ################################
crop_property_damage_log<- ggplot(df, aes(prop_dmg_log))
crop_property_damage_log + geom_histogram(binwidth = 1)
### economic dimension VS causality log normalized plot
cor.test(df$causality_log, df$per_below_poverty_norm) #okay
##
## Pearson's product-moment correlation
##
## data: df$causality_log and df$per_below_poverty_norm
## t = -4.864, df = 3131, p-value = 1.207e-06
## alternative hypothesis: true correlation is not equal to 0
## 95 percent confidence interval:
## -0.12125061 -0.05173809
## sample estimates:
## cor
## -0.08659975
cor.test(df$causality_log, df$median_hh_income_1999_norm)#okay # remove because highly correlated with per_below_poverty_norm and college
##
## Pearson's product-moment correlation
##
## data: df$causality_log and df$median_hh_income_1999_norm
## t = 13.492, df = 3131, p-value < 2.2e-16
## alternative hypothesis: true correlation is not equal to 0
## 95 percent confidence interval:
## 0.2010409 0.2672341
## sample estimates:
## cor
## 0.2344092
cor.test(df$causality_log, df$per_rent_norm)# okay
##
## Pearson's product-moment correlation
##
## data: df$causality_log and df$per_rent_norm
## t = 11.816, df = 3131, p-value < 2.2e-16
## alternative hypothesis: true correlation is not equal to 0
## 95 percent confidence interval:
## 0.1728367 0.2398877
## sample estimates:
## cor
## 0.2066048
cor.test(df$causality_log, df$per_no_carnorm)#okay
##
## Pearson's product-moment correlation
##
## data: df$causality_log and df$per_no_carnorm
## t = 3.5238, df = 3131, p-value = 0.0004314
## alternative hypothesis: true correlation is not equal to 0
## 95 percent confidence interval:
## 0.02789407 0.09765486
## sample estimates:
## cor
## 0.06285124
cor.test(df$causality_log, df$per_college_or_higher_norm)# okay
##
## Pearson's product-moment correlation
##
## data: df$causality_log and df$per_college_or_higher_norm
## t = 14.726, df = 3131, p-value < 2.2e-16
## alternative hypothesis: true correlation is not equal to 0
## 95 percent confidence interval:
## 0.2214552 0.2869612
## sample estimates:
## cor
## 0.2545001
cor.test(df$causality_log, df$average_hh_norm)#okay
##
## Pearson's product-moment correlation
##
## data: df$causality_log and df$average_hh_norm
## t = 4.7925, df = 3131, p-value = 1.724e-06
## alternative hypothesis: true correlation is not equal to 0
## 95 percent confidence interval:
## 0.05046896 0.11999667
## sample estimates:
## cor
## 0.0853367
cor.test(df$causality_log, df$per_lack_plumbing_norm)#okay
##
## Pearson's product-moment correlation
##
## data: df$causality_log and df$per_lack_plumbing_norm
## t = -6.1403, df = 3131, p-value = 9.271e-10
## alternative hypothesis: true correlation is not equal to 0
## 95 percent confidence interval:
## -0.14355171 -0.07434693
## sample estimates:
## cor
## -0.1090815
cor.test(df$causality_log, df$per_lack_kitchen_norm) #okay # remove because highly correlated with lack of plumbing
##
## Pearson's product-moment correlation
##
## data: df$causality_log and df$per_lack_kitchen_norm
## t = -8.9688, df = 3131, p-value < 2.2e-16
## alternative hypothesis: true correlation is not equal to 0
## 95 percent confidence interval:
## -0.1922176 -0.1239327
## sample estimates:
## cor
## -0.1582644
cor.test(df$causality_log, df$per_mobile_home_norm)#okay
##
## Pearson's product-moment correlation
##
## data: df$causality_log and df$per_mobile_home_norm
## t = -7.6441, df = 3131, p-value = 2.78e-14
## alternative hypothesis: true correlation is not equal to 0
## 95 percent confidence interval:
## -0.1695680 -0.1008124
## sample estimates:
## cor
## -0.1353532
cor.test(df$causality_log, df$per_unemployed_norm)## not statistically significant
##
## Pearson's product-moment correlation
##
## data: df$causality_log and df$per_unemployed_norm
## t = -0.2848, df = 3131, p-value = 0.7758
## alternative hypothesis: true correlation is not equal to 0
## 95 percent confidence interval:
## -0.04010104 0.02993427
## sample estimates:
## cor
## -0.00508963
X<-df%>%
select(
per_below_poverty_norm,
per_rent_norm,
per_no_carnorm,
per_college_or_higher_norm,
per_lack_plumbing_norm,
per_mobile_home_norm)
ggpairs(X)
econ_causality <- lm(causality_log~(per_below_poverty_norm+
per_rent_norm+
per_no_carnorm+
per_college_or_higher_norm+
per_lack_plumbing_norm+
per_mobile_home_norm)+
log_pop_2000+numb_haz_log+state,data=df, na.rm=TRUE)
## Warning: In lm.fit(x, y, offset = offset, singular.ok = singular.ok, ...) :
## extra argument 'na.rm' will be disregarded
summary(econ_causality)
##
## Call:
## lm(formula = causality_log ~ (per_below_poverty_norm + per_rent_norm +
## per_no_carnorm + per_college_or_higher_norm + per_lack_plumbing_norm +
## per_mobile_home_norm) + log_pop_2000 + numb_haz_log + state,
## data = df, na.rm = TRUE)
##
## Residuals:
## Min 1Q Median 3Q Max
## -2.5649 -0.6535 -0.1070 0.5386 4.3432
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) -3.982480 0.352838 -11.287 < 2e-16 ***
## per_below_poverty_norm -0.080377 0.040967 -1.962 0.04986 *
## per_rent_norm 0.056487 0.027526 2.052 0.04024 *
## per_no_carnorm 0.003174 0.035302 0.090 0.92836
## per_college_or_higher_norm 0.048820 0.026003 1.878 0.06054 .
## per_lack_plumbing_norm 0.070948 0.028053 2.529 0.01149 *
## per_mobile_home_norm 0.024085 0.029251 0.823 0.41035
## log_pop_2000 0.373100 0.019920 18.730 < 2e-16 ***
## numb_haz_log 0.678154 0.048996 13.841 < 2e-16 ***
## stateAL 0.989367 0.325817 3.037 0.00241 **
## stateAR 0.535397 0.318726 1.680 0.09310 .
## stateAZ 0.794574 0.383972 2.069 0.03860 *
## stateCA -0.073217 0.323236 -0.227 0.82082
## stateCO 0.601070 0.319147 1.883 0.05975 .
## stateCT -0.498626 0.448735 -1.111 0.26658
## stateDE 1.128203 0.627761 1.797 0.07240 .
## stateFL 0.645392 0.327770 1.969 0.04904 *
## stateGA 0.065672 0.311770 0.211 0.83318
## stateIA -0.127175 0.313010 -0.406 0.68455
## stateID 0.545231 0.333562 1.635 0.10224
## stateIL 0.372610 0.313049 1.190 0.23404
## stateIN -0.016515 0.314229 -0.053 0.95809
## stateKS 0.440469 0.312215 1.411 0.15841
## stateKY 0.227268 0.312897 0.726 0.46769
## stateLA 0.295365 0.327545 0.902 0.36726
## stateMA -0.210612 0.388963 -0.541 0.58822
## stateMD 0.365951 0.354146 1.033 0.30153
## stateME -0.011515 0.372229 -0.031 0.97532
## stateMI -0.022618 0.312870 -0.072 0.94237
## stateMN 0.037174 0.312476 0.119 0.90531
## stateMO 0.823752 0.310364 2.654 0.00799 **
## stateMS 0.477720 0.324328 1.473 0.14087
## stateMT 0.702936 0.326026 2.156 0.03116 *
## stateNC -0.106752 0.315246 -0.339 0.73491
## stateND 0.182730 0.325561 0.561 0.57465
## stateNE 0.307618 0.315240 0.976 0.32923
## stateNH 0.297931 0.420599 0.708 0.47878
## stateNJ 0.506725 0.360563 1.405 0.16001
## stateNM 0.012378 0.343806 0.036 0.97128
## stateNV 0.875480 0.380453 2.301 0.02145 *
## stateNY -0.284331 0.315079 -0.902 0.36691
## stateOH -0.412280 0.314662 -1.310 0.19022
## stateOK 0.261583 0.320127 0.817 0.41392
## stateOR -0.206217 0.338200 -0.610 0.54207
## statePA -0.009654 0.313816 -0.031 0.97546
## stateRI -0.330060 0.561082 -0.588 0.55640
## stateSC 0.400225 0.334803 1.195 0.23202
## stateSD 0.367743 0.324548 1.133 0.25726
## stateTN 0.337236 0.316683 1.065 0.28701
## stateTX 0.298378 0.305037 0.978 0.32807
## stateUT 1.065270 0.344410 3.093 0.00200 **
## stateVA -0.270206 0.305956 -0.883 0.37722
## stateVT -0.491323 0.387453 -1.268 0.20486
## stateWA 0.269121 0.334443 0.805 0.42106
## stateWI -0.048814 0.313436 -0.156 0.87625
## stateWV -0.143369 0.321466 -0.446 0.65564
## stateWY 0.553211 0.358973 1.541 0.12340
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.9546 on 3065 degrees of freedom
## (11 observations deleted due to missingness)
## Multiple R-squared: 0.384, Adjusted R-squared: 0.3728
## F-statistic: 34.12 on 56 and 3065 DF, p-value: < 2.2e-16
cor.test(df$causality_log, df$life_expectancy_2000_norm) # not okay
##
## Pearson's product-moment correlation
##
## data: df$causality_log and df$life_expectancy_2000_norm
## t = -0.82059, df = 3131, p-value = 0.4119
## alternative hypothesis: true correlation is not equal to 0
## 95 percent confidence interval:
## -0.04965661 0.02036547
## sample estimates:
## cor
## -0.01466355
cor.test(df$causality_log, df$per_hypertension_2001_norm)# OKAY # remove due to high correlation
##
## Pearson's product-moment correlation
##
## data: df$causality_log and df$per_hypertension_2001_norm
## t = -2.4116, df = 3131, p-value = 0.01594
## alternative hypothesis: true correlation is not equal to 0
## 95 percent confidence interval:
## -0.077960119 -0.008052692
## sample estimates:
## cor
## -0.04305911
# cor.test(df$causality_log, df$per_heart_disease_35_65_norm)# not okay
# cor.test(df$causality_log, df$per_heart_disease_65_more_norm)# not okay
# cor.test(df$causality_log, df$per_stroke_35_65_norm) # OKAY
# cor.test(df$causality_log, df$per_stroke_65_more_norm) #not okay
cor.test(df$causality_log, df$per_diabetes_2000_norm)# not okay
##
## Pearson's product-moment correlation
##
## data: df$causality_log and df$per_diabetes_2000_norm
## t = -0.80988, df = 3131, p-value = 0.4181
## alternative hypothesis: true correlation is not equal to 0
## 95 percent confidence interval:
## -0.04946562 0.02055686
## sample estimates:
## cor
## -0.01447212
cor.test(df$causality_log, df$per_disability_norm)# OKAY
##
## Pearson's product-moment correlation
##
## data: df$causality_log and df$per_disability_norm
## t = -3.3577, df = 3131, p-value = 0.0007954
## alternative hypothesis: true correlation is not equal to 0
## 95 percent confidence interval:
## -0.09471831 -0.02493216
## sample estimates:
## cor
## -0.05989842
cor.test(df$causality_log, df$per_nursingnorm)# OKAY
##
## Pearson's product-moment correlation
##
## data: df$causality_log and df$per_nursingnorm
## t = -10.242, df = 3131, p-value < 2.2e-16
## alternative hypothesis: true correlation is not equal to 0
## 95 percent confidence interval:
## -0.2137186 -0.1459492
## sample estimates:
## cor
## -0.1800475
X<-df%>%
select(
per_disability_norm,
per_nursingnorm)
ggpairs(X)
health_causality <- lm(causality_log~(
per_disability_norm+
per_nursingnorm)+
log_pop_2000+numb_haz_log+state,data=df, na.rm=TRUE)
## Warning: In lm.fit(x, y, offset = offset, singular.ok = singular.ok, ...) :
## extra argument 'na.rm' will be disregarded
summary(health_causality)
##
## Call:
## lm(formula = causality_log ~ (per_disability_norm + per_nursingnorm) +
## log_pop_2000 + numb_haz_log + state, data = df, na.rm = TRUE)
##
## Residuals:
## Min 1Q Median 3Q Max
## -2.5182 -0.6635 -0.0972 0.5381 4.3410
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) -3.599314 0.254992 -14.115 < 2e-16 ***
## per_disability_norm -0.008189 0.024371 -0.336 0.736879
## per_nursingnorm -0.017086 0.020115 -0.849 0.395709
## log_pop_2000 0.395212 0.017102 23.109 < 2e-16 ***
## numb_haz_log 0.670764 0.049000 13.689 < 2e-16 ***
## stateAL 0.338424 0.253420 1.335 0.181835
## stateAR -0.079760 0.249973 -0.319 0.749691
## stateAZ 0.214814 0.332258 0.647 0.517986
## stateCA -0.637680 0.255133 -2.499 0.012492 *
## stateCO 0.104764 0.246562 0.425 0.670938
## stateCT -1.026559 0.405623 -2.531 0.011429 *
## stateDE 0.533533 0.595910 0.895 0.370684
## stateFL 0.015181 0.252694 0.060 0.952098
## stateGA -0.548739 0.232381 -2.361 0.018269 *
## stateIA -0.708081 0.238273 -2.972 0.002984 **
## stateID -0.035843 0.260253 -0.138 0.890466
## stateIL -0.236635 0.238047 -0.994 0.320267
## stateIN -0.621284 0.241262 -2.575 0.010066 *
## stateKS -0.104524 0.237014 -0.441 0.659242
## stateKY -0.408352 0.240989 -1.694 0.090275 .
## stateLA -0.388484 0.251085 -1.547 0.121913
## stateMA -0.700398 0.339819 -2.061 0.039378 *
## stateMD -0.205337 0.294270 -0.698 0.485365
## stateME -0.541491 0.326093 -1.661 0.096908 .
## stateMI -0.641287 0.242474 -2.645 0.008216 **
## stateMN -0.552613 0.241006 -2.293 0.021918 *
## stateMO 0.221749 0.237254 0.935 0.350042
## stateMS -0.200866 0.246794 -0.814 0.415765
## stateMT 0.165590 0.253190 0.654 0.513151
## stateNC -0.704214 0.242245 -2.907 0.003675 **
## stateND -0.384153 0.253496 -1.515 0.129769
## stateNE -0.234485 0.239199 -0.980 0.327019
## stateNH -0.206410 0.374381 -0.551 0.581444
## stateNJ -0.038764 0.306412 -0.127 0.899337
## stateNM -0.575211 0.274941 -2.092 0.036509 *
## stateNV 0.348571 0.318791 1.093 0.274298
## stateNY -0.845044 0.252303 -3.349 0.000820 ***
## stateOH -1.031752 0.242904 -4.248 2.23e-05 ***
## stateOK -0.350427 0.246297 -1.423 0.154900
## stateOR -0.751280 0.270321 -2.779 0.005482 **
## statePA -0.610288 0.249650 -2.445 0.014558 *
## stateRI -0.847416 0.527437 -1.607 0.108230
## stateSC -0.232418 0.264232 -0.880 0.379146
## stateSD -0.203003 0.247533 -0.820 0.412221
## stateTN -0.293260 0.244218 -1.201 0.229917
## stateTX -0.306213 0.226686 -1.351 0.176853
## stateUT 0.497085 0.278815 1.783 0.074710 .
## stateVA -0.826948 0.233684 -3.539 0.000408 ***
## stateVT -1.000771 0.334966 -2.988 0.002833 **
## stateWA -0.280852 0.268566 -1.046 0.295761
## stateWI -0.624061 0.245303 -2.544 0.011006 *
## stateWV -0.777076 0.257726 -3.015 0.002590 **
## stateWY 0.034153 0.294374 0.116 0.907644
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.957 on 3069 degrees of freedom
## (11 observations deleted due to missingness)
## Multiple R-squared: 0.3801, Adjusted R-squared: 0.3696
## F-statistic: 36.18 on 52 and 3069 DF, p-value: < 2.2e-16
cor.test(df$causality_log, df$FEMA_total_norm) # okay
##
## Pearson's product-moment correlation
##
## data: df$causality_log and df$FEMA_total_norm
## t = 10.953, df = 3131, p-value < 2.2e-16
## alternative hypothesis: true correlation is not equal to 0
## 95 percent confidence interval:
## 0.1581372 0.2255931
## sample estimates:
## cor
## 0.192092
cor.test(df$causality_log, df$number_research_institutions_norm) # okay
##
## Pearson's product-moment correlation
##
## data: df$causality_log and df$number_research_institutions_norm
## t = 13.29, df = 3131, p-value < 2.2e-16
## alternative hypothesis: true correlation is not equal to 0
## 95 percent confidence interval:
## 0.1976626 0.2639642
## sample estimates:
## cor
## 0.2310816
cor.test(df$causality_log, df$employees_2001_norm) # okay
##
## Pearson's product-moment correlation
##
## data: df$causality_log and df$employees_2001_norm
## t = 19.836, df = 3131, p-value < 2.2e-16
## alternative hypothesis: true correlation is not equal to 0
## 95 percent confidence interval:
## 0.3026446 0.3648715
## sample estimates:
## cor
## 0.3341221
X<-df%>%
select(
FEMA_total,
number_research_institutions,
employees_2001)
ggpairs(X)
inst_causality <- lm(causality_log~(FEMA_total_norm+
number_research_institutions_norm+
employees_2001_norm)+
log_pop_2000+numb_haz_log+state,data=df, na.rm=TRUE)
## Warning: In lm.fit(x, y, offset = offset, singular.ok = singular.ok, ...) :
## extra argument 'na.rm' will be disregarded
summary(inst_causality)
##
## Call:
## lm(formula = causality_log ~ (FEMA_total_norm + number_research_institutions_norm +
## employees_2001_norm) + log_pop_2000 + numb_haz_log + state,
## data = df, na.rm = TRUE)
##
## Residuals:
## Min 1Q Median 3Q Max
## -2.6884 -0.6568 -0.1011 0.5372 4.3724
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) -3.08671 0.26265 -11.752 < 2e-16 ***
## FEMA_total_norm 0.10397 0.01790 5.807 7.02e-09 ***
## number_research_institutions_norm 0.04246 0.02170 1.956 0.050508 .
## employees_2001_norm 0.07875 0.02386 3.300 0.000976 ***
## log_pop_2000 0.34395 0.01763 19.510 < 2e-16 ***
## numb_haz_log 0.68021 0.04843 14.044 < 2e-16 ***
## stateAL 0.35147 0.24236 1.450 0.147107
## stateAR -0.08232 0.23862 -0.345 0.730118
## stateAZ 0.22265 0.32534 0.684 0.493806
## stateCA -0.71355 0.24958 -2.859 0.004278 **
## stateCO 0.10436 0.24300 0.429 0.667613
## stateCT -1.00925 0.39928 -2.528 0.011532 *
## stateDE 0.57499 0.58822 0.978 0.328392
## stateFL -0.06835 0.24378 -0.280 0.779193
## stateGA -0.53550 0.22494 -2.381 0.017344 *
## stateIA -0.71817 0.23239 -3.090 0.002017 **
## stateID -0.03406 0.25636 -0.133 0.894328
## stateIL -0.23062 0.23219 -0.993 0.320664
## stateIN -0.59069 0.23453 -2.519 0.011833 *
## stateKS -0.14452 0.23083 -0.626 0.531294
## stateKY -0.41236 0.22896 -1.801 0.071798 .
## stateLA -0.48288 0.24412 -1.978 0.048017 *
## stateMA -0.75500 0.33450 -2.257 0.024073 *
## stateMD -0.15630 0.28884 -0.541 0.588459
## stateME -0.48716 0.31954 -1.525 0.127472
## stateMI -0.60613 0.23703 -2.557 0.010600 *
## stateMN -0.54009 0.23557 -2.293 0.021931 *
## stateMO 0.21693 0.22960 0.945 0.344836
## stateMS -0.23919 0.23707 -1.009 0.313094
## stateMT 0.13557 0.24859 0.545 0.585556
## stateNC -0.67369 0.23318 -2.889 0.003891 **
## stateND -0.43910 0.24840 -1.768 0.077205 .
## stateNE -0.28803 0.23327 -1.235 0.217022
## stateNH -0.14381 0.36831 -0.390 0.696222
## stateNJ 0.01179 0.30025 0.039 0.968692
## stateNM -0.56461 0.26888 -2.100 0.035821 *
## stateNV 0.35312 0.31315 1.128 0.259562
## stateNY -0.86173 0.24660 -3.494 0.000482 ***
## stateOH -0.99456 0.23639 -4.207 2.66e-05 ***
## stateOK -0.36006 0.23801 -1.513 0.130429
## stateOR -0.72344 0.26517 -2.728 0.006403 **
## statePA -0.55982 0.24399 -2.294 0.021832 *
## stateRI -0.85590 0.52132 -1.642 0.100736
## stateSC -0.18870 0.25514 -0.740 0.459595
## stateSD -0.24147 0.24294 -0.994 0.320336
## stateTN -0.28151 0.23360 -1.205 0.228255
## stateTX -0.33473 0.21995 -1.522 0.128143
## stateUT 0.49607 0.27530 1.802 0.071654 .
## stateVA -0.80542 0.22758 -3.539 0.000407 ***
## stateVT -0.96781 0.33036 -2.930 0.003419 **
## stateWA -0.26146 0.26277 -0.995 0.319807
## stateWI -0.58868 0.24040 -2.449 0.014392 *
## stateWV -0.76913 0.24763 -3.106 0.001913 **
## stateWY 0.03571 0.29000 0.123 0.901998
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.9461 on 3068 degrees of freedom
## (11 observations deleted due to missingness)
## Multiple R-squared: 0.3944, Adjusted R-squared: 0.384
## F-statistic: 37.7 on 53 and 3068 DF, p-value: < 2.2e-16
cor.test(df$causality_log, df$air_quality_norm)#okay
##
## Pearson's product-moment correlation
##
## data: df$causality_log and df$air_quality_norm
## t = 20.882, df = 3120, p-value < 2.2e-16
## alternative hypothesis: true correlation is not equal to 0
## 95 percent confidence interval:
## 0.3190083 0.3805750
## sample estimates:
## cor
## 0.3501698
cor.test(df$causality_log, df$water_quality_norm)# not statistically significant
##
## Pearson's product-moment correlation
##
## data: df$causality_log and df$water_quality_norm
## t = 0.54829, df = 3120, p-value = 0.5835
## alternative hypothesis: true correlation is not equal to 0
## 95 percent confidence interval:
## -0.02527340 0.04488026
## sample estimates:
## cor
## 0.009815506
cor.test(df$causality_log, df$built_quality_norm)#okay
##
## Pearson's product-moment correlation
##
## data: df$causality_log and df$built_quality_norm
## t = 14.999, df = 3120, p-value < 2.2e-16
## alternative hypothesis: true correlation is not equal to 0
## 95 percent confidence interval:
## 0.2263162 0.2917633
## sample estimates:
## cor
## 0.2593375
cor.test(df$causality_log, df$land_quality_norm)#not statistically significan
##
## Pearson's product-moment correlation
##
## data: df$causality_log and df$land_quality_norm
## t = -0.78107, df = 3120, p-value = 0.4348
## alternative hypothesis: true correlation is not equal to 0
## 95 percent confidence interval:
## -0.04903820 0.02110851
## sample estimates:
## cor
## -0.01398205
cor.test(df$causality_log, df$impervious_surface_norm)#okay
##
## Pearson's product-moment correlation
##
## data: df$causality_log and df$impervious_surface_norm
## t = 16.106, df = 3120, p-value < 2.2e-16
## alternative hypothesis: true correlation is not equal to 0
## 95 percent confidence interval:
## 0.2443535 0.3091345
## sample estimates:
## cor
## 0.2770588
X<-df%>%
select(
air_quality_norm,
built_quality_norm,
impervious_surface_norm)
ggpairs(X)
## Warning: Removed 11 rows containing non-finite values (`stat_density()`).
## Warning in ggally_statistic(data = data, mapping = mapping, na.rm = na.rm, :
## Removed 11 rows containing missing values
## Warning in ggally_statistic(data = data, mapping = mapping, na.rm = na.rm, :
## Removed 11 rows containing missing values
## Warning: Removed 11 rows containing missing values (`geom_point()`).
## Warning: Removed 11 rows containing non-finite values (`stat_density()`).
## Warning in ggally_statistic(data = data, mapping = mapping, na.rm = na.rm, :
## Removed 11 rows containing missing values
## Warning: Removed 11 rows containing missing values (`geom_point()`).
## Removed 11 rows containing missing values (`geom_point()`).
## Warning: Removed 11 rows containing non-finite values (`stat_density()`).
environ_causality <- lm(causality_log~(air_quality_norm+
built_quality_norm+
impervious_surface_norm)+
log_pop_2000+numb_haz_log+state,data=df, na.rm=TRUE)
## Warning: In lm.fit(x, y, offset = offset, singular.ok = singular.ok, ...) :
## extra argument 'na.rm' will be disregarded
summary(environ_causality)
##
## Call:
## lm(formula = causality_log ~ (air_quality_norm + built_quality_norm +
## impervious_surface_norm) + log_pop_2000 + numb_haz_log +
## state, data = df, na.rm = TRUE)
##
## Residuals:
## Min 1Q Median 3Q Max
## -2.6721 -0.6632 -0.1004 0.5426 4.4066
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) -4.716808 0.411355 -11.467 < 2e-16 ***
## air_quality_norm -0.222995 0.045630 -4.887 1.08e-06 ***
## built_quality_norm 0.007076 0.021814 0.324 0.74568
## impervious_surface_norm 0.109649 0.021469 5.107 3.47e-07 ***
## log_pop_2000 0.474253 0.030792 15.402 < 2e-16 ***
## numb_haz_log 0.687336 0.048840 14.073 < 2e-16 ***
## stateAL 0.680344 0.254964 2.668 0.00766 **
## stateAR 0.154530 0.245971 0.628 0.52989
## stateAZ 0.403402 0.328784 1.227 0.21993
## stateCA -0.472170 0.252360 -1.871 0.06144 .
## stateCO 0.161579 0.244716 0.660 0.50913
## stateCT -0.743136 0.406302 -1.829 0.06749 .
## stateDE 0.801704 0.593205 1.351 0.17664
## stateFL 0.238785 0.249738 0.956 0.33908
## stateGA -0.208053 0.239390 -0.869 0.38486
## stateIA -0.412339 0.243320 -1.695 0.09025 .
## stateID 0.239088 0.263664 0.907 0.36459
## stateIL 0.117975 0.247082 0.477 0.63306
## stateIN -0.209991 0.252899 -0.830 0.40641
## stateKS 0.094281 0.237696 0.397 0.69166
## stateKY -0.027444 0.246169 -0.111 0.91124
## stateLA -0.012255 0.257839 -0.048 0.96209
## stateMA -0.548262 0.341200 -1.607 0.10819
## stateMD 0.143967 0.300700 0.479 0.63213
## stateME -0.209761 0.327271 -0.641 0.52161
## stateMI -0.357101 0.246128 -1.451 0.14692
## stateMN -0.319086 0.242636 -1.315 0.18858
## stateMO 0.492934 0.239694 2.057 0.03982 *
## stateMS 0.180566 0.252909 0.714 0.47531
## stateMT 0.263939 0.251006 1.052 0.29310
## stateNC -0.343017 0.246729 -1.390 0.16455
## stateND -0.233808 0.253114 -0.924 0.35570
## stateNE -0.045317 0.240176 -0.189 0.85035
## stateNH 0.129117 0.375881 0.344 0.73124
## stateNJ 0.152805 0.311542 0.490 0.62383
## stateNM -0.386943 0.272616 -1.419 0.15589
## stateNV 0.503350 0.316320 1.591 0.11165
## stateNY -0.582357 0.256085 -2.274 0.02303 *
## stateOH -0.652128 0.252280 -2.585 0.00979 **
## stateOK -0.125074 0.244999 -0.511 0.60973
## stateOR -0.357151 0.277761 -1.286 0.19860
## statePA -0.250306 0.256522 -0.976 0.32926
## stateRI -0.667879 0.529584 -1.261 0.20735
## stateSC 0.156454 0.268457 0.583 0.56008
## stateSD -0.062023 0.246904 -0.251 0.80167
## stateTN 0.073942 0.248854 0.297 0.76639
## stateTX -0.057894 0.228645 -0.253 0.80013
## stateUT 0.647403 0.278307 2.326 0.02007 *
## stateVA -0.539447 0.246161 -2.191 0.02849 *
## stateVT -0.706707 0.337046 -2.097 0.03610 *
## stateWA 0.007356 0.270288 0.027 0.97829
## stateWI -0.301898 0.250944 -1.203 0.22905
## stateWV -0.354784 0.266088 -1.333 0.18252
## stateWY 0.256180 0.295313 0.867 0.38574
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.9502 on 3068 degrees of freedom
## (11 observations deleted due to missingness)
## Multiple R-squared: 0.3891, Adjusted R-squared: 0.3786
## F-statistic: 36.88 on 53 and 3068 DF, p-value: < 2.2e-16
X<-df%>%
select(per_black_norm,
per_hispanic_norm,
per_asian_norm,
per_american_indian_norm,
per_elderly_norm,
per_young_dependent_norm,
per_female_hh_with_kids_under6_norm,
per_rural_norm,
per_below_poverty_norm,
per_rent_norm,
per_no_carnorm,
per_college_or_higher_norm,
per_lack_plumbing_norm,
per_mobile_home_norm,
per_disability_norm,
per_nursingnorm,
FEMA_total_norm,
number_research_institutions_norm,
employees_2001_norm,
air_quality_norm,
built_quality_norm,
impervious_surface_norm)
ggpairs(X)
## Warning in ggally_statistic(data = data, mapping = mapping, na.rm = na.rm, :
## Removed 11 rows containing missing values
## Warning in ggally_statistic(data = data, mapping = mapping, na.rm = na.rm, :
## Removed 11 rows containing missing values
## Warning in ggally_statistic(data = data, mapping = mapping, na.rm = na.rm, :
## Removed 11 rows containing missing values
## Warning in ggally_statistic(data = data, mapping = mapping, na.rm = na.rm, :
## Removed 11 rows containing missing values
## Warning in ggally_statistic(data = data, mapping = mapping, na.rm = na.rm, :
## Removed 11 rows containing missing values
## Warning in ggally_statistic(data = data, mapping = mapping, na.rm = na.rm, :
## Removed 11 rows containing missing values
## Warning in ggally_statistic(data = data, mapping = mapping, na.rm = na.rm, :
## Removed 11 rows containing missing values
## Warning in ggally_statistic(data = data, mapping = mapping, na.rm = na.rm, :
## Removed 11 rows containing missing values
## Warning in ggally_statistic(data = data, mapping = mapping, na.rm = na.rm, :
## Removed 11 rows containing missing values
## Warning in ggally_statistic(data = data, mapping = mapping, na.rm = na.rm, :
## Removed 11 rows containing missing values
## Warning in ggally_statistic(data = data, mapping = mapping, na.rm = na.rm, :
## Removed 11 rows containing missing values
## Warning in ggally_statistic(data = data, mapping = mapping, na.rm = na.rm, :
## Removed 11 rows containing missing values
## Warning in ggally_statistic(data = data, mapping = mapping, na.rm = na.rm, :
## Removed 11 rows containing missing values
## Warning in ggally_statistic(data = data, mapping = mapping, na.rm = na.rm, :
## Removed 11 rows containing missing values
## Warning in ggally_statistic(data = data, mapping = mapping, na.rm = na.rm, :
## Removed 11 rows containing missing values
## Warning in ggally_statistic(data = data, mapping = mapping, na.rm = na.rm, :
## Removed 11 rows containing missing values
## Warning in ggally_statistic(data = data, mapping = mapping, na.rm = na.rm, :
## Removed 11 rows containing missing values
## Warning in ggally_statistic(data = data, mapping = mapping, na.rm = na.rm, :
## Removed 11 rows containing missing values
## Warning in ggally_statistic(data = data, mapping = mapping, na.rm = na.rm, :
## Removed 11 rows containing missing values
## Warning in ggally_statistic(data = data, mapping = mapping, na.rm = na.rm, :
## Removed 11 rows containing missing values
## Warning in ggally_statistic(data = data, mapping = mapping, na.rm = na.rm, :
## Removed 11 rows containing missing values
## Warning in ggally_statistic(data = data, mapping = mapping, na.rm = na.rm, :
## Removed 11 rows containing missing values
## Warning in ggally_statistic(data = data, mapping = mapping, na.rm = na.rm, :
## Removed 11 rows containing missing values
## Warning in ggally_statistic(data = data, mapping = mapping, na.rm = na.rm, :
## Removed 11 rows containing missing values
## Warning in ggally_statistic(data = data, mapping = mapping, na.rm = na.rm, :
## Removed 11 rows containing missing values
## Warning in ggally_statistic(data = data, mapping = mapping, na.rm = na.rm, :
## Removed 11 rows containing missing values
## Warning in ggally_statistic(data = data, mapping = mapping, na.rm = na.rm, :
## Removed 11 rows containing missing values
## Warning in ggally_statistic(data = data, mapping = mapping, na.rm = na.rm, :
## Removed 11 rows containing missing values
## Warning in ggally_statistic(data = data, mapping = mapping, na.rm = na.rm, :
## Removed 11 rows containing missing values
## Warning in ggally_statistic(data = data, mapping = mapping, na.rm = na.rm, :
## Removed 11 rows containing missing values
## Warning in ggally_statistic(data = data, mapping = mapping, na.rm = na.rm, :
## Removed 11 rows containing missing values
## Warning in ggally_statistic(data = data, mapping = mapping, na.rm = na.rm, :
## Removed 11 rows containing missing values
## Warning in ggally_statistic(data = data, mapping = mapping, na.rm = na.rm, :
## Removed 11 rows containing missing values
## Warning in ggally_statistic(data = data, mapping = mapping, na.rm = na.rm, :
## Removed 11 rows containing missing values
## Warning in ggally_statistic(data = data, mapping = mapping, na.rm = na.rm, :
## Removed 11 rows containing missing values
## Warning in ggally_statistic(data = data, mapping = mapping, na.rm = na.rm, :
## Removed 11 rows containing missing values
## Warning in ggally_statistic(data = data, mapping = mapping, na.rm = na.rm, :
## Removed 11 rows containing missing values
## Warning in ggally_statistic(data = data, mapping = mapping, na.rm = na.rm, :
## Removed 11 rows containing missing values
## Warning in ggally_statistic(data = data, mapping = mapping, na.rm = na.rm, :
## Removed 11 rows containing missing values
## Warning in ggally_statistic(data = data, mapping = mapping, na.rm = na.rm, :
## Removed 11 rows containing missing values
## Warning in ggally_statistic(data = data, mapping = mapping, na.rm = na.rm, :
## Removed 11 rows containing missing values
## Warning in ggally_statistic(data = data, mapping = mapping, na.rm = na.rm, :
## Removed 11 rows containing missing values
## Warning in ggally_statistic(data = data, mapping = mapping, na.rm = na.rm, :
## Removed 11 rows containing missing values
## Warning in ggally_statistic(data = data, mapping = mapping, na.rm = na.rm, :
## Removed 11 rows containing missing values
## Warning in ggally_statistic(data = data, mapping = mapping, na.rm = na.rm, :
## Removed 11 rows containing missing values
## Warning in ggally_statistic(data = data, mapping = mapping, na.rm = na.rm, :
## Removed 11 rows containing missing values
## Warning in ggally_statistic(data = data, mapping = mapping, na.rm = na.rm, :
## Removed 11 rows containing missing values
## Warning in ggally_statistic(data = data, mapping = mapping, na.rm = na.rm, :
## Removed 11 rows containing missing values
## Warning in ggally_statistic(data = data, mapping = mapping, na.rm = na.rm, :
## Removed 11 rows containing missing values
## Warning in ggally_statistic(data = data, mapping = mapping, na.rm = na.rm, :
## Removed 11 rows containing missing values
## Warning in ggally_statistic(data = data, mapping = mapping, na.rm = na.rm, :
## Removed 11 rows containing missing values
## Warning in ggally_statistic(data = data, mapping = mapping, na.rm = na.rm, :
## Removed 11 rows containing missing values
## Warning in ggally_statistic(data = data, mapping = mapping, na.rm = na.rm, :
## Removed 11 rows containing missing values
## Warning in ggally_statistic(data = data, mapping = mapping, na.rm = na.rm, :
## Removed 11 rows containing missing values
## Warning in ggally_statistic(data = data, mapping = mapping, na.rm = na.rm, :
## Removed 11 rows containing missing values
## Warning in ggally_statistic(data = data, mapping = mapping, na.rm = na.rm, :
## Removed 11 rows containing missing values
## Warning in ggally_statistic(data = data, mapping = mapping, na.rm = na.rm, :
## Removed 11 rows containing missing values
## Warning: Removed 11 rows containing missing values (`geom_point()`).
## Removed 11 rows containing missing values (`geom_point()`).
## Removed 11 rows containing missing values (`geom_point()`).
## Removed 11 rows containing missing values (`geom_point()`).
## Removed 11 rows containing missing values (`geom_point()`).
## Removed 11 rows containing missing values (`geom_point()`).
## Removed 11 rows containing missing values (`geom_point()`).
## Removed 11 rows containing missing values (`geom_point()`).
## Removed 11 rows containing missing values (`geom_point()`).
## Removed 11 rows containing missing values (`geom_point()`).
## Removed 11 rows containing missing values (`geom_point()`).
## Removed 11 rows containing missing values (`geom_point()`).
## Removed 11 rows containing missing values (`geom_point()`).
## Removed 11 rows containing missing values (`geom_point()`).
## Removed 11 rows containing missing values (`geom_point()`).
## Removed 11 rows containing missing values (`geom_point()`).
## Removed 11 rows containing missing values (`geom_point()`).
## Removed 11 rows containing missing values (`geom_point()`).
## Removed 11 rows containing missing values (`geom_point()`).
## Warning: Removed 11 rows containing non-finite values (`stat_density()`).
## Warning in ggally_statistic(data = data, mapping = mapping, na.rm = na.rm, :
## Removed 11 rows containing missing values
## Warning in ggally_statistic(data = data, mapping = mapping, na.rm = na.rm, :
## Removed 11 rows containing missing values
## Warning: Removed 11 rows containing missing values (`geom_point()`).
## Removed 11 rows containing missing values (`geom_point()`).
## Removed 11 rows containing missing values (`geom_point()`).
## Removed 11 rows containing missing values (`geom_point()`).
## Removed 11 rows containing missing values (`geom_point()`).
## Removed 11 rows containing missing values (`geom_point()`).
## Removed 11 rows containing missing values (`geom_point()`).
## Removed 11 rows containing missing values (`geom_point()`).
## Removed 11 rows containing missing values (`geom_point()`).
## Removed 11 rows containing missing values (`geom_point()`).
## Removed 11 rows containing missing values (`geom_point()`).
## Removed 11 rows containing missing values (`geom_point()`).
## Removed 11 rows containing missing values (`geom_point()`).
## Removed 11 rows containing missing values (`geom_point()`).
## Removed 11 rows containing missing values (`geom_point()`).
## Removed 11 rows containing missing values (`geom_point()`).
## Removed 11 rows containing missing values (`geom_point()`).
## Removed 11 rows containing missing values (`geom_point()`).
## Removed 11 rows containing missing values (`geom_point()`).
## Removed 11 rows containing missing values (`geom_point()`).
## Warning: Removed 11 rows containing non-finite values (`stat_density()`).
## Warning in ggally_statistic(data = data, mapping = mapping, na.rm = na.rm, :
## Removed 11 rows containing missing values
## Warning: Removed 11 rows containing missing values (`geom_point()`).
## Removed 11 rows containing missing values (`geom_point()`).
## Removed 11 rows containing missing values (`geom_point()`).
## Removed 11 rows containing missing values (`geom_point()`).
## Removed 11 rows containing missing values (`geom_point()`).
## Removed 11 rows containing missing values (`geom_point()`).
## Removed 11 rows containing missing values (`geom_point()`).
## Removed 11 rows containing missing values (`geom_point()`).
## Removed 11 rows containing missing values (`geom_point()`).
## Removed 11 rows containing missing values (`geom_point()`).
## Removed 11 rows containing missing values (`geom_point()`).
## Removed 11 rows containing missing values (`geom_point()`).
## Removed 11 rows containing missing values (`geom_point()`).
## Removed 11 rows containing missing values (`geom_point()`).
## Removed 11 rows containing missing values (`geom_point()`).
## Removed 11 rows containing missing values (`geom_point()`).
## Removed 11 rows containing missing values (`geom_point()`).
## Removed 11 rows containing missing values (`geom_point()`).
## Removed 11 rows containing missing values (`geom_point()`).
## Removed 11 rows containing missing values (`geom_point()`).
## Removed 11 rows containing missing values (`geom_point()`).
## Warning: Removed 11 rows containing non-finite values (`stat_density()`).
model_causality <- lm(causality_log~(per_black_norm+
per_hispanic_norm+
per_asian_norm+
per_american_indian_norm+
per_elderly_norm+
per_young_dependent_norm+
per_female_hh_with_kids_under6_norm+
per_rural_norm+
per_below_poverty_norm+
per_rent_norm+
per_no_carnorm+
per_college_or_higher_norm+
per_lack_plumbing_norm+
per_mobile_home_norm+
per_disability_norm+
per_nursingnorm+
FEMA_total_norm+
number_research_institutions_norm+
employees_2001_norm+
air_quality_norm+
built_quality_norm+
impervious_surface_norm)+log_pop_2000+numb_haz_log+state,data=df, na.rm=TRUE)
## Warning: In lm.fit(x, y, offset = offset, singular.ok = singular.ok, ...) :
## extra argument 'na.rm' will be disregarded
summary(model_causality)
##
## Call:
## lm(formula = causality_log ~ (per_black_norm + per_hispanic_norm +
## per_asian_norm + per_american_indian_norm + per_elderly_norm +
## per_young_dependent_norm + per_female_hh_with_kids_under6_norm +
## per_rural_norm + per_below_poverty_norm + per_rent_norm +
## per_no_carnorm + per_college_or_higher_norm + per_lack_plumbing_norm +
## per_mobile_home_norm + per_disability_norm + per_nursingnorm +
## FEMA_total_norm + number_research_institutions_norm + employees_2001_norm +
## air_quality_norm + built_quality_norm + impervious_surface_norm) +
## log_pop_2000 + numb_haz_log + state, data = df, na.rm = TRUE)
##
## Residuals:
## Min 1Q Median 3Q Max
## -2.5257 -0.6503 -0.1046 0.5292 4.4376
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) -4.1295888 0.5014068 -8.236 2.61e-16 ***
## per_black_norm 0.0782379 0.0349964 2.236 0.025450 *
## per_hispanic_norm 0.0334940 0.0487624 0.687 0.492210
## per_asian_norm -0.1274496 0.0344885 -3.695 0.000223 ***
## per_american_indian_norm 0.0460675 0.0278878 1.652 0.098661 .
## per_elderly_norm 0.0471320 0.0356038 1.324 0.185671
## per_young_dependent_norm 0.0023073 0.0330683 0.070 0.944379
## per_female_hh_with_kids_under6_norm -0.0235208 0.0359975 -0.653 0.513547
## per_rural_norm -0.0006099 0.0386973 -0.016 0.987426
## per_below_poverty_norm -0.1473569 0.0494348 -2.981 0.002897 **
## per_rent_norm 0.0686678 0.0340468 2.017 0.043797 *
## per_no_carnorm -0.0969694 0.0404784 -2.396 0.016654 *
## per_college_or_higher_norm 0.0594780 0.0331587 1.794 0.072955 .
## per_lack_plumbing_norm 0.0386440 0.0295750 1.307 0.191431
## per_mobile_home_norm 0.0583878 0.0323373 1.806 0.071081 .
## per_disability_norm 0.0404351 0.0390782 1.035 0.300880
## per_nursingnorm -0.0323389 0.0233934 -1.382 0.166951
## FEMA_total_norm 0.0995506 0.0178811 5.567 2.81e-08 ***
## number_research_institutions_norm 0.0425839 0.0232127 1.835 0.066676 .
## employees_2001_norm 0.0555001 0.0261918 2.119 0.034172 *
## air_quality_norm -0.1873809 0.0514384 -3.643 0.000274 ***
## built_quality_norm -0.0007746 0.0250669 -0.031 0.975349
## impervious_surface_norm 0.1102979 0.0272639 4.046 5.35e-05 ***
## log_pop_2000 0.4291093 0.0358200 11.980 < 2e-16 ***
## numb_haz_log 0.6840068 0.0489292 13.980 < 2e-16 ***
## stateAL 0.5307972 0.3571002 1.486 0.137274
## stateAR 0.0460665 0.3446009 0.134 0.893664
## stateAZ 0.1301507 0.4045613 0.322 0.747696
## stateCA -0.4796600 0.3391579 -1.414 0.157385
## stateCO -0.0338030 0.3357255 -0.101 0.919806
## stateCT -0.9440840 0.4646924 -2.032 0.042277 *
## stateDE 0.5864810 0.6342614 0.925 0.355212
## stateFL -0.1188168 0.3589015 -0.331 0.740624
## stateGA -0.3926038 0.3421609 -1.147 0.251296
## stateIA -0.5291097 0.3359087 -1.575 0.115323
## stateID 0.0808992 0.3528691 0.229 0.818681
## stateIL 0.0090136 0.3394437 0.027 0.978817
## stateIN -0.3183960 0.3421512 -0.931 0.352149
## stateKS -0.0967265 0.3352136 -0.289 0.772944
## stateKY -0.0515151 0.3458494 -0.149 0.881601
## stateLA -0.1668469 0.3583762 -0.466 0.641561
## stateMA -0.7718993 0.4129984 -1.869 0.061717 .
## stateMD 0.0080794 0.3766909 0.021 0.982889
## stateME -0.3525904 0.3949355 -0.893 0.372046
## stateMI -0.4717241 0.3355265 -1.406 0.159849
## stateMN -0.3799790 0.3300326 -1.151 0.249684
## stateMO 0.4038508 0.3356213 1.203 0.228956
## stateMS 0.0216887 0.3606576 0.060 0.952051
## stateMT 0.0964389 0.3429819 0.281 0.778593
## stateNC -0.5809914 0.3472649 -1.673 0.094420 .
## stateND -0.4039929 0.3449074 -1.171 0.241566
## stateNE -0.2236737 0.3385464 -0.661 0.508862
## stateNH -0.0712797 0.4379697 -0.163 0.870726
## stateNJ 0.1402226 0.3839816 0.365 0.715002
## stateNM -0.5671149 0.3726528 -1.522 0.128155
## stateNV 0.2270100 0.3937347 0.577 0.564282
## stateNY -0.6791204 0.3391260 -2.003 0.045313 *
## stateOH -0.7383586 0.3426491 -2.155 0.031251 *
## stateOK -0.2973004 0.3415152 -0.871 0.384077
## stateOR -0.5759378 0.3634182 -1.585 0.113120
## statePA -0.3585331 0.3434673 -1.044 0.296631
## stateRI -0.8990581 0.5793549 -1.552 0.120808
## stateSC -0.0589762 0.3666944 -0.161 0.872236
## stateSD -0.2204046 0.3428528 -0.643 0.520367
## stateTN -0.0378903 0.3471057 -0.109 0.913082
## stateTX -0.2215196 0.3358333 -0.660 0.509553
## stateUT 0.5046767 0.3648607 1.383 0.166704
## stateVA -0.7409463 0.3417316 -2.168 0.030220 *
## stateVT -0.8927646 0.4042211 -2.209 0.027276 *
## stateWA -0.1099006 0.3521889 -0.312 0.755024
## stateWI -0.4262870 0.3349966 -1.273 0.203289
## stateWV -0.3716637 0.3558655 -1.044 0.296386
## stateWY 0.0330549 0.3741976 0.088 0.929616
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.9384 on 3049 degrees of freedom
## (11 observations deleted due to missingness)
## Multiple R-squared: 0.4079, Adjusted R-squared: 0.3939
## F-statistic: 29.17 on 72 and 3049 DF, p-value: < 2.2e-16
### economic dimension VS causality log normalized plot
cor.test(df$prop_dmg_log, df$per_below_poverty_norm) #okay
##
## Pearson's product-moment correlation
##
## data: df$prop_dmg_log and df$per_below_poverty_norm
## t = -4.4995, df = 3131, p-value = 7.059e-06
## alternative hypothesis: true correlation is not equal to 0
## 95 percent confidence interval:
## -0.1148502 -0.0452625
## sample estimates:
## cor
## -0.08015401
cor.test(df$prop_dmg_log, df$median_hh_income_1999_norm)##okay- highly correlated
##
## Pearson's product-moment correlation
##
## data: df$prop_dmg_log and df$median_hh_income_1999_norm
## t = 10.827, df = 3131, p-value < 2.2e-16
## alternative hypothesis: true correlation is not equal to 0
## 95 percent confidence interval:
## 0.1559898 0.2235024
## sample estimates:
## cor
## 0.1899707
cor.test(df$prop_dmg_log, df$per_rent_norm)# okay
##
## Pearson's product-moment correlation
##
## data: df$prop_dmg_log and df$per_rent_norm
## t = 4.9541, df = 3131, p-value = 7.652e-07
## alternative hypothesis: true correlation is not equal to 0
## 95 percent confidence interval:
## 0.05333773 0.12283078
## sample estimates:
## cor
## 0.08819156
cor.test(df$prop_dmg_log, df$per_no_carnorm)# okay
##
## Pearson's product-moment correlation
##
## data: df$prop_dmg_log and df$per_no_carnorm
## t = 3.5701, df = 3131, p-value = 0.0003621
## alternative hypothesis: true correlation is not equal to 0
## 95 percent confidence interval:
## 0.02871948 0.09847300
## sample estimates:
## cor
## 0.06367401
cor.test(df$prop_dmg_log, df$per_college_or_higher_norm)# okay
##
## Pearson's product-moment correlation
##
## data: df$prop_dmg_log and df$per_college_or_higher_norm
## t = 7.8065, df = 3131, p-value = 7.957e-15
## alternative hypothesis: true correlation is not equal to 0
## 95 percent confidence interval:
## 0.1036575 0.1723590
## sample estimates:
## cor
## 0.1381745
cor.test(df$prop_dmg_log, df$average_hh_norm)##okay
##
## Pearson's product-moment correlation
##
## data: df$prop_dmg_log and df$average_hh_norm
## t = 2.119, df = 3131, p-value = 0.03417
## alternative hypothesis: true correlation is not equal to 0
## 95 percent confidence interval:
## 0.002826967 0.072763920
## sample estimates:
## cor
## 0.03784178
cor.test(df$prop_dmg_log, df$per_lack_plumbing_norm)##okay
##
## Pearson's product-moment correlation
##
## data: df$prop_dmg_log and df$per_lack_plumbing_norm
## t = -7.1554, df = 3131, p-value = 1.035e-12
## alternative hypothesis: true correlation is not equal to 0
## 95 percent confidence interval:
## -0.16114655 -0.09223492
## sample estimates:
## cor
## -0.1268438
cor.test(df$prop_dmg_log, df$per_lack_kitchen_norm) # okay - highly correlated
##
## Pearson's product-moment correlation
##
## data: df$prop_dmg_log and df$per_lack_kitchen_norm
## t = -10.585, df = 3131, p-value < 2.2e-16
## alternative hypothesis: true correlation is not equal to 0
## 95 percent confidence interval:
## -0.2194695 -0.1518493
## sample estimates:
## cor
## -0.1858795
cor.test(df$prop_dmg_log, df$per_mobile_home_norm)# okay
##
## Pearson's product-moment correlation
##
## data: df$prop_dmg_log and df$per_mobile_home_norm
## t = -8.5314, df = 3131, p-value < 2.2e-16
## alternative hypothesis: true correlation is not equal to 0
## 95 percent confidence interval:
## -0.1847693 -0.1163214
## sample estimates:
## cor
## -0.150726
cor.test(df$prop_dmg_log, df$per_unemployed_norm)## #not statistically significant
##
## Pearson's product-moment correlation
##
## data: df$prop_dmg_log and df$per_unemployed_norm
## t = 0.41851, df = 3131, p-value = 0.6756
## alternative hypothesis: true correlation is not equal to 0
## 95 percent confidence interval:
## -0.02754666 0.04248655
## sample estimates:
## cor
## 0.007479114
X<-df%>%
select(
per_below_poverty_norm,
per_rent_norm,
per_no_carnorm,
per_college_or_higher_norm,
average_hh_norm,
per_lack_plumbing_norm,
per_mobile_home_norm)
ggpairs(X)
econ_damage <- lm(prop_dmg_log ~per_below_poverty_norm+
per_rent_norm+
per_no_carnorm+
per_college_or_higher_norm+
average_hh_norm+
per_lack_plumbing_norm+
per_mobile_home_norm+
log_pop_2000+numb_haz_log+state+log_median_house_value,data=df, na.rm=TRUE)
## Warning: In lm.fit(x, y, offset = offset, singular.ok = singular.ok, ...) :
## extra argument 'na.rm' will be disregarded
summary(econ_damage)
##
## Call:
## lm(formula = prop_dmg_log ~ per_below_poverty_norm + per_rent_norm +
## per_no_carnorm + per_college_or_higher_norm + average_hh_norm +
## per_lack_plumbing_norm + per_mobile_home_norm + log_pop_2000 +
## numb_haz_log + state + log_median_house_value, data = df,
## na.rm = TRUE)
##
## Residuals:
## Min 1Q Median 3Q Max
## -14.0507 -1.0482 0.0025 1.0550 8.8419
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 3.356163 2.391451 1.403 0.160599
## per_below_poverty_norm 0.220520 0.098810 2.232 0.025703 *
## per_rent_norm -0.207350 0.057265 -3.621 0.000298 ***
## per_no_carnorm -0.088058 0.074049 -1.189 0.234457
## per_college_or_higher_norm -0.007501 0.068486 -0.110 0.912793
## average_hh_norm -0.156698 0.050525 -3.101 0.001944 **
## per_lack_plumbing_norm -0.038468 0.058612 -0.656 0.511666
## per_mobile_home_norm -0.042269 0.063573 -0.665 0.506175
## log_pop_2000 0.639834 0.045769 13.980 < 2e-16 ***
## numb_haz_log 3.164582 0.101824 31.079 < 2e-16 ***
## stateAL -3.533324 0.689793 -5.122 3.21e-07 ***
## stateAR -2.320939 0.677324 -3.427 0.000619 ***
## stateAZ -4.022354 0.802693 -5.011 5.72e-07 ***
## stateCA -2.043206 0.674736 -3.028 0.002481 **
## stateCO -3.646247 0.668627 -5.453 5.34e-08 ***
## stateCT -5.387472 0.937751 -5.745 1.01e-08 ***
## stateDE -3.123608 1.308039 -2.388 0.017000 *
## stateFL -1.967288 0.696083 -2.826 0.004741 **
## stateGA -3.234417 0.655637 -4.933 8.52e-07 ***
## stateIA -1.899870 0.665609 -2.854 0.004342 **
## stateID -4.987693 0.695220 -7.174 9.08e-13 ***
## stateIL -3.271902 0.665277 -4.918 9.20e-07 ***
## stateIN -2.573331 0.661940 -3.888 0.000103 ***
## stateKS -1.742517 0.670351 -2.599 0.009383 **
## stateKY -2.467604 0.661722 -3.729 0.000196 ***
## stateLA -0.704704 0.688865 -1.023 0.306392
## stateMA -3.425639 0.814934 -4.204 2.70e-05 ***
## stateMD -2.843168 0.741353 -3.835 0.000128 ***
## stateME -1.883788 0.787559 -2.392 0.016820 *
## stateMI -3.708275 0.661710 -5.604 2.28e-08 ***
## stateMN -2.194817 0.661412 -3.318 0.000916 ***
## stateMO -2.740000 0.659545 -4.154 3.35e-05 ***
## stateMS -1.707062 0.683584 -2.497 0.012569 *
## stateMT -4.196362 0.688040 -6.099 1.20e-09 ***
## stateNC -3.184429 0.666707 -4.776 1.87e-06 ***
## stateND -2.364448 0.698446 -3.385 0.000720 ***
## stateNE -1.782870 0.672454 -2.651 0.008060 **
## stateNH -2.277807 0.883056 -2.579 0.009942 **
## stateNJ -2.956273 0.752812 -3.927 8.79e-05 ***
## stateNM -3.478517 0.722869 -4.812 1.57e-06 ***
## stateNV -2.215734 0.795404 -2.786 0.005375 **
## stateNY -3.181351 0.666951 -4.770 1.93e-06 ***
## stateOH -1.990489 0.662889 -3.003 0.002697 **
## stateOK -2.401261 0.686179 -3.499 0.000473 ***
## stateOR -3.270460 0.709541 -4.609 4.21e-06 ***
## statePA -3.400208 0.667360 -5.095 3.70e-07 ***
## stateRI -4.938629 1.169344 -4.223 2.48e-05 ***
## stateSC -3.516205 0.707792 -4.968 7.14e-07 ***
## stateSD -3.038163 0.691708 -4.392 1.16e-05 ***
## stateTN -3.267222 0.669204 -4.882 1.10e-06 ***
## stateTX -2.571488 0.650983 -3.950 7.99e-05 ***
## stateUT -3.580711 0.716547 -4.997 6.14e-07 ***
## stateVA -3.037916 0.644537 -4.713 2.55e-06 ***
## stateVT -2.971947 0.813581 -3.653 0.000264 ***
## stateWA -2.729914 0.700437 -3.897 9.93e-05 ***
## stateWI -2.384231 0.661169 -3.606 0.000316 ***
## stateWV -2.314410 0.682798 -3.390 0.000709 ***
## stateWY -4.237404 0.753263 -5.625 2.02e-08 ***
## log_median_house_value 0.210134 0.208086 1.010 0.312650
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 1.98 on 3063 degrees of freedom
## (11 observations deleted due to missingness)
## Multiple R-squared: 0.5284, Adjusted R-squared: 0.5195
## F-statistic: 59.18 on 58 and 3063 DF, p-value: < 2.2e-16
cor.test(df$prop_dmg_log, df$life_expectancy_2000_norm) # okay- highly correlated
##
## Pearson's product-moment correlation
##
## data: df$prop_dmg_log and df$life_expectancy_2000_norm
## t = -2.3914, df = 3131, p-value = 0.01684
## alternative hypothesis: true correlation is not equal to 0
## 95 percent confidence interval:
## -0.077600882 -0.007691291
## sample estimates:
## cor
## -0.04269835
cor.test(df$prop_dmg_log, df$per_hypertension_2001_norm)# okay
##
## Pearson's product-moment correlation
##
## data: df$prop_dmg_log and df$per_hypertension_2001_norm
## t = 2.3197, df = 3131, p-value = 0.02042
## alternative hypothesis: true correlation is not equal to 0
## 95 percent confidence interval:
## 0.006411454 0.076328564
## sample estimates:
## cor
## 0.04142072
cor.test(df$prop_dmg_log, df$per_heart_disease_35_65_norm)# okay- highly correlated
##
## Pearson's product-moment correlation
##
## data: df$prop_dmg_log and df$per_heart_disease_35_65_norm
## t = 3.1247, df = 3131, p-value = 0.001796
## alternative hypothesis: true correlation is not equal to 0
## 95 percent confidence interval:
## 0.02077725 0.09059692
## sample estimates:
## cor
## 0.05575525
cor.test(df$prop_dmg_log, df$per_heart_disease_65_more_norm)# okay
##
## Pearson's product-moment correlation
##
## data: df$prop_dmg_log and df$per_heart_disease_65_more_norm
## t = 6.545, df = 3131, p-value = 6.926e-11
## alternative hypothesis: true correlation is not equal to 0
## 95 percent confidence interval:
## 0.08148891 0.15058190
## sample estimates:
## cor
## 0.116176
cor.test(df$prop_dmg_log, df$per_stroke_35_65_norm) # okay- highly correlated
##
## Pearson's product-moment correlation
##
## data: df$prop_dmg_log and df$per_stroke_35_65_norm
## t = 5.2268, df = 3131, p-value = 1.838e-07
## alternative hypothesis: true correlation is not equal to 0
## 95 percent confidence interval:
## 0.05817545 0.12760750
## sample estimates:
## cor
## 0.09300454
cor.test(df$prop_dmg_log, df$per_stroke_65_more_norm) #not statistically significant
##
## Pearson's product-moment correlation
##
## data: df$prop_dmg_log and df$per_stroke_65_more_norm
## t = 1.6926, df = 3131, p-value = 0.09064
## alternative hypothesis: true correlation is not equal to 0
## 95 percent confidence interval:
## -0.004789138 0.065184041
## sample estimates:
## cor
## 0.03023449
cor.test(df$prop_dmg_log, df$per_diabetes_2000_norm)# okay - highly correlated
##
## Pearson's product-moment correlation
##
## data: df$prop_dmg_log and df$per_diabetes_2000_norm
## t = 3.2074, df = 3131, p-value = 0.001353
## alternative hypothesis: true correlation is not equal to 0
## 95 percent confidence interval:
## 0.02225242 0.09206047
## sample estimates:
## cor
## 0.05722639
cor.test(df$prop_dmg_log, df$per_disability_norm)# not statistically significant
##
## Pearson's product-moment correlation
##
## data: df$prop_dmg_log and df$per_disability_norm
## t = -0.11328, df = 3131, p-value = 0.9098
## alternative hypothesis: true correlation is not equal to 0
## 95 percent confidence interval:
## -0.03704049 0.03299635
## sample estimates:
## cor
## -0.002024552
cor.test(df$prop_dmg_log, df$per_nursingnorm)# okay
##
## Pearson's product-moment correlation
##
## data: df$prop_dmg_log and df$per_nursingnorm
## t = -4.3561, df = 3131, p-value = 1.367e-05
## alternative hypothesis: true correlation is not equal to 0
## 95 percent confidence interval:
## -0.11232721 -0.04271147
## sample estimates:
## cor
## -0.07761394
X<-df%>%
select(
per_hypertension_2001_norm,
per_nursingnorm)
ggpairs(X)
health_damage <- lm(prop_dmg_log~(per_hypertension_2001_norm+
per_nursingnorm)+
log_pop_2000+numb_haz_log+state,data=df, na.rm=TRUE)
## Warning: In lm.fit(x, y, offset = offset, singular.ok = singular.ok, ...) :
## extra argument 'na.rm' will be disregarded
summary(health_damage)
##
## Call:
## lm(formula = prop_dmg_log ~ (per_hypertension_2001_norm + per_nursingnorm) +
## log_pop_2000 + numb_haz_log + state, data = df, na.rm = TRUE)
##
## Residuals:
## Min 1Q Median 3Q Max
## -13.8780 -1.0369 -0.0143 1.0453 8.9753
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 5.202368 0.531300 9.792 < 2e-16 ***
## per_hypertension_2001_norm -0.007955 0.055687 -0.143 0.886423
## per_nursingnorm 0.068345 0.041849 1.633 0.102541
## log_pop_2000 0.581669 0.035570 16.353 < 2e-16 ***
## numb_haz_log 3.203125 0.101641 31.514 < 2e-16 ***
## stateAL -2.343805 0.528351 -4.436 9.48e-06 ***
## stateAR -1.306833 0.512843 -2.548 0.010876 *
## stateAZ -3.001020 0.683763 -4.389 1.18e-05 ***
## stateCA -1.076515 0.524319 -2.053 0.040141 *
## stateCO -2.567863 0.511893 -5.016 5.56e-07 ***
## stateCT -4.286533 0.840458 -5.100 3.60e-07 ***
## stateDE -1.950870 1.235296 -1.579 0.114377
## stateFL -0.711080 0.515234 -1.380 0.167653
## stateGA -2.229510 0.485585 -4.591 4.58e-06 ***
## stateIA -0.917385 0.494013 -1.857 0.063406 .
## stateID -3.982854 0.539324 -7.385 1.96e-13 ***
## stateIL -2.208568 0.493637 -4.474 7.95e-06 ***
## stateIN -1.544671 0.499051 -3.095 0.001984 **
## stateKS -0.836752 0.490659 -1.705 0.088228 .
## stateKY -1.343949 0.491456 -2.735 0.006281 **
## stateLA 0.399539 0.528566 0.756 0.449772
## stateMA -2.359404 0.701980 -3.361 0.000786 ***
## stateMD -1.757167 0.610915 -2.876 0.004052 **
## stateME -0.684480 0.672550 -1.018 0.308883
## stateMI -2.450927 0.500414 -4.898 1.02e-06 ***
## stateMN -1.086625 0.499770 -2.174 0.029762 *
## stateMO -1.710246 0.489180 -3.496 0.000479 ***
## stateMS -0.596559 0.522144 -1.143 0.253328
## stateMT -3.163960 0.525077 -6.026 1.88e-09 ***
## stateNC -2.044930 0.499608 -4.093 4.37e-05 ***
## stateND -1.402488 0.525754 -2.668 0.007680 **
## stateNE -0.925869 0.496295 -1.866 0.062198 .
## stateNH -1.233165 0.775217 -1.591 0.111772
## stateNJ -1.976154 0.634165 -3.116 0.001849 **
## stateNM -2.340536 0.565504 -4.139 3.58e-05 ***
## stateNV -1.238805 0.657486 -1.884 0.059638 .
## stateNY -2.220393 0.520609 -4.265 2.06e-05 ***
## stateOH -0.922869 0.503256 -1.834 0.066781 .
## stateOK -1.359796 0.506362 -2.685 0.007283 **
## stateOR -2.220876 0.557464 -3.984 6.94e-05 ***
## statePA -2.259489 0.515834 -4.380 1.23e-05 ***
## stateRI -3.888239 1.093184 -3.557 0.000381 ***
## stateSC -2.382545 0.551792 -4.318 1.63e-05 ***
## stateSD -2.170384 0.513378 -4.228 2.43e-05 ***
## stateTN -2.122642 0.500581 -4.240 2.30e-05 ***
## stateTX -1.635730 0.466663 -3.505 0.000463 ***
## stateUT -2.749720 0.578481 -4.753 2.09e-06 ***
## stateVA -1.963022 0.483720 -4.058 5.07e-05 ***
## stateVT -1.883574 0.694525 -2.712 0.006725 **
## stateWA -1.668328 0.553219 -3.016 0.002585 **
## stateWI -1.305897 0.508240 -2.569 0.010233 *
## stateWV -1.087072 0.527235 -2.062 0.039307 *
## stateWY -3.207940 0.610831 -5.252 1.61e-07 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 1.986 on 3069 degrees of freedom
## (11 observations deleted due to missingness)
## Multiple R-squared: 0.5245, Adjusted R-squared: 0.5165
## F-statistic: 65.11 on 52 and 3069 DF, p-value: < 2.2e-16
df$predict_health_damage <- predict(health_damage, newdata = df)
cor.test(df$prop_dmg_log, df$FEMA_total_norm) # okay
##
## Pearson's product-moment correlation
##
## data: df$prop_dmg_log and df$FEMA_total_norm
## t = 11.268, df = 3131, p-value < 2.2e-16
## alternative hypothesis: true correlation is not equal to 0
## 95 percent confidence interval:
## 0.1635275 0.2308383
## sample estimates:
## cor
## 0.1974156
cor.test(df$prop_dmg_log, df$number_research_institutions_norm) # okay
##
## Pearson's product-moment correlation
##
## data: df$prop_dmg_log and df$number_research_institutions_norm
## t = 7.3935, df = 3131, p-value = 1.826e-13
## alternative hypothesis: true correlation is not equal to 0
## 95 percent confidence interval:
## 0.09641749 0.16525427
## sample estimates:
## cor
## 0.1309938
cor.test(df$prop_dmg_log, df$employees_2001_norm) # okay
##
## Pearson's product-moment correlation
##
## data: df$prop_dmg_log and df$employees_2001_norm
## t = 11.935, df = 3131, p-value < 2.2e-16
## alternative hypothesis: true correlation is not equal to 0
## 95 percent confidence interval:
## 0.1748624 0.2418554
## sample estimates:
## cor
## 0.2086036
X<-df%>%
select(
FEMA_total_norm,
number_research_institutions_norm,
employees_2001_norm)
ggpairs(X)
inst_damage <- lm(prop_dmg_log~(FEMA_total_norm+
number_research_institutions_norm+
employees_2001_norm)+
log_pop_2000+numb_haz_log+state,data=df, na.rm=TRUE)
## Warning: In lm.fit(x, y, offset = offset, singular.ok = singular.ok, ...) :
## extra argument 'na.rm' will be disregarded
summary(inst_damage)
##
## Call:
## lm(formula = prop_dmg_log ~ (FEMA_total_norm + number_research_institutions_norm +
## employees_2001_norm) + log_pop_2000 + numb_haz_log + state,
## data = df, na.rm = TRUE)
##
## Residuals:
## Min 1Q Median 3Q Max
## -13.8799 -1.0137 -0.0012 1.0548 9.0461
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 5.17897 0.54627 9.481 < 2e-16 ***
## FEMA_total_norm 0.28143 0.03724 7.557 5.39e-14 ***
## number_research_institutions_norm 0.04567 0.04514 1.012 0.311789
## employees_2001_norm -0.14648 0.04962 -2.952 0.003183 **
## log_pop_2000 0.57325 0.03667 15.634 < 2e-16 ***
## numb_haz_log 3.22387 0.10073 32.004 < 2e-16 ***
## stateAL -2.28419 0.50406 -4.532 6.08e-06 ***
## stateAR -1.22507 0.49628 -2.469 0.013622 *
## stateAZ -2.85437 0.67666 -4.218 2.53e-05 ***
## stateCA -0.83277 0.51908 -1.604 0.108746
## stateCO -2.49598 0.50540 -4.939 8.29e-07 ***
## stateCT -4.08755 0.83043 -4.922 9.01e-07 ***
## stateDE -1.91872 1.22339 -1.568 0.116900
## stateFL -0.90958 0.50702 -1.794 0.072913 .
## stateGA -2.17938 0.46783 -4.658 3.32e-06 ***
## stateIA -0.81979 0.48332 -1.696 0.089958 .
## stateID -3.92081 0.53319 -7.354 2.46e-13 ***
## stateIL -2.07303 0.48292 -4.293 1.82e-05 ***
## stateIN -1.42322 0.48778 -2.918 0.003551 **
## stateKS -0.72064 0.48009 -1.501 0.133440
## stateKY -1.24882 0.47619 -2.622 0.008772 **
## stateLA 0.13522 0.50773 0.266 0.790015
## stateMA -2.25037 0.69571 -3.235 0.001231 **
## stateMD -1.63743 0.60073 -2.726 0.006453 **
## stateME -0.59332 0.66458 -0.893 0.372053
## stateMI -2.35596 0.49298 -4.779 1.84e-06 ***
## stateMN -0.95705 0.48994 -1.953 0.050862 .
## stateMO -1.60350 0.47753 -3.358 0.000795 ***
## stateMS -0.67333 0.49307 -1.366 0.172164
## stateMT -3.05902 0.51703 -5.917 3.65e-09 ***
## stateNC -1.97540 0.48498 -4.073 4.76e-05 ***
## stateND -1.30715 0.51662 -2.530 0.011449 *
## stateNE -0.79342 0.48516 -1.635 0.102074
## stateNH -1.13463 0.76602 -1.481 0.138655
## stateNJ -1.75920 0.62448 -2.817 0.004877 **
## stateNM -2.27930 0.55921 -4.076 4.70e-05 ***
## stateNV -1.18226 0.65131 -1.815 0.069589 .
## stateNY -2.09060 0.51289 -4.076 4.70e-05 ***
## stateOH -0.79158 0.49166 -1.610 0.107495
## stateOK -1.29463 0.49501 -2.615 0.008957 **
## stateOR -2.14685 0.55150 -3.893 0.000101 ***
## statePA -2.14701 0.50745 -4.231 2.40e-05 ***
## stateRI -3.82813 1.08425 -3.531 0.000421 ***
## stateSC -2.31633 0.53064 -4.365 1.31e-05 ***
## stateSD -2.06948 0.50528 -4.096 4.32e-05 ***
## stateTN -2.01893 0.48584 -4.156 3.33e-05 ***
## stateTX -1.57068 0.45745 -3.434 0.000604 ***
## stateUT -2.70130 0.57257 -4.718 2.49e-06 ***
## stateVA -1.89546 0.47332 -4.005 6.36e-05 ***
## stateVT -1.84325 0.68709 -2.683 0.007342 **
## stateWA -1.57210 0.54652 -2.877 0.004048 **
## stateWI -1.19721 0.49999 -2.394 0.016705 *
## stateWV -1.00856 0.51502 -1.958 0.050284 .
## stateWY -3.12801 0.60315 -5.186 2.29e-07 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 1.968 on 3068 degrees of freedom
## (11 observations deleted due to missingness)
## Multiple R-squared: 0.5334, Adjusted R-squared: 0.5253
## F-statistic: 66.17 on 53 and 3068 DF, p-value: < 2.2e-16
cor.test(df$prop_dmg_log, df$air_quality_norm)#okay
##
## Pearson's product-moment correlation
##
## data: df$prop_dmg_log and df$air_quality_norm
## t = 24.727, df = 3120, p-value < 2.2e-16
## alternative hypothesis: true correlation is not equal to 0
## 95 percent confidence interval:
## 0.3750345 0.4337107
## sample estimates:
## cor
## 0.4047892
cor.test(df$prop_dmg_log, df$water_quality_norm)#
##
## Pearson's product-moment correlation
##
## data: df$prop_dmg_log and df$water_quality_norm
## t = -3.2292, df = 3120, p-value = 0.001254
## alternative hypothesis: true correlation is not equal to 0
## 95 percent confidence interval:
## -0.09260756 -0.02268057
## sample estimates:
## cor
## -0.05771485
cor.test(df$prop_dmg_log, df$built_quality_norm)#okay
##
## Pearson's product-moment correlation
##
## data: df$prop_dmg_log and df$built_quality_norm
## t = 11.678, df = 3120, p-value < 2.2e-16
## alternative hypothesis: true correlation is not equal to 0
## 95 percent confidence interval:
## 0.1707847 0.2380104
## sample estimates:
## cor
## 0.2046389
cor.test(df$prop_dmg_log, df$land_quality_norm)#not
##
## Pearson's product-moment correlation
##
## data: df$prop_dmg_log and df$land_quality_norm
## t = -3.3154, df = 3120, p-value = 0.0009257
## alternative hypothesis: true correlation is not equal to 0
## 95 percent confidence interval:
## -0.09413459 -0.02422018
## sample estimates:
## cor
## -0.05925005
cor.test(df$prop_dmg_log, df$impervious_surface_norm)#okay
##
## Pearson's product-moment correlation
##
## data: df$prop_dmg_log and df$impervious_surface_norm
## t = 10.456, df = 3120, p-value < 2.2e-16
## alternative hypothesis: true correlation is not equal to 0
## 95 percent confidence interval:
## 0.1498774 0.2176656
## sample estimates:
## cor
## 0.1839903
X<-df%>%
select(
air_quality_norm,
water_quality_norm,
built_quality_norm,
land_quality_norm,
impervious_surface_norm)
ggpairs(X)
## Warning: Removed 11 rows containing non-finite values (`stat_density()`).
## Warning in ggally_statistic(data = data, mapping = mapping, na.rm = na.rm, :
## Removed 11 rows containing missing values
## Warning in ggally_statistic(data = data, mapping = mapping, na.rm = na.rm, :
## Removed 11 rows containing missing values
## Warning in ggally_statistic(data = data, mapping = mapping, na.rm = na.rm, :
## Removed 11 rows containing missing values
## Warning in ggally_statistic(data = data, mapping = mapping, na.rm = na.rm, :
## Removed 11 rows containing missing values
## Warning: Removed 11 rows containing missing values (`geom_point()`).
## Warning: Removed 11 rows containing non-finite values (`stat_density()`).
## Warning in ggally_statistic(data = data, mapping = mapping, na.rm = na.rm, :
## Removed 11 rows containing missing values
## Warning in ggally_statistic(data = data, mapping = mapping, na.rm = na.rm, :
## Removed 11 rows containing missing values
## Warning in ggally_statistic(data = data, mapping = mapping, na.rm = na.rm, :
## Removed 11 rows containing missing values
## Warning: Removed 11 rows containing missing values (`geom_point()`).
## Removed 11 rows containing missing values (`geom_point()`).
## Warning: Removed 11 rows containing non-finite values (`stat_density()`).
## Warning in ggally_statistic(data = data, mapping = mapping, na.rm = na.rm, :
## Removed 11 rows containing missing values
## Warning in ggally_statistic(data = data, mapping = mapping, na.rm = na.rm, :
## Removed 11 rows containing missing values
## Warning: Removed 11 rows containing missing values (`geom_point()`).
## Removed 11 rows containing missing values (`geom_point()`).
## Removed 11 rows containing missing values (`geom_point()`).
## Warning: Removed 11 rows containing non-finite values (`stat_density()`).
## Warning in ggally_statistic(data = data, mapping = mapping, na.rm = na.rm, :
## Removed 11 rows containing missing values
## Warning: Removed 11 rows containing missing values (`geom_point()`).
## Removed 11 rows containing missing values (`geom_point()`).
## Removed 11 rows containing missing values (`geom_point()`).
## Removed 11 rows containing missing values (`geom_point()`).
## Warning: Removed 11 rows containing non-finite values (`stat_density()`).
env_damage <- lm(prop_dmg_log~(air_quality_norm+
water_quality_norm+
built_quality_norm+
land_quality_norm+
impervious_surface_norm
)+
log_pop_2000+numb_haz_log+state,data=df, na.rm=TRUE)
## Warning: In lm.fit(x, y, offset = offset, singular.ok = singular.ok, ...) :
## extra argument 'na.rm' will be disregarded
summary(env_damage)
##
## Call:
## lm(formula = prop_dmg_log ~ (air_quality_norm + water_quality_norm +
## built_quality_norm + land_quality_norm + impervious_surface_norm) +
## log_pop_2000 + numb_haz_log + state, data = df, na.rm = TRUE)
##
## Residuals:
## Min 1Q Median 3Q Max
## -13.9693 -1.0335 -0.0088 1.0625 9.0844
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 4.265220 0.939079 4.542 5.79e-06 ***
## air_quality_norm -0.011171 0.095350 -0.117 0.906742
## water_quality_norm -0.113025 0.062836 -1.799 0.072158 .
## built_quality_norm 0.024125 0.045656 0.528 0.597259
## land_quality_norm -0.099272 0.056761 -1.749 0.080400 .
## impervious_surface_norm -0.065701 0.046143 -1.424 0.154591
## log_pop_2000 0.611765 0.065474 9.344 < 2e-16 ***
## numb_haz_log 3.211074 0.102207 31.417 < 2e-16 ***
## stateAL -1.954281 0.591821 -3.302 0.000970 ***
## stateAR -0.666944 0.583395 -1.143 0.253040
## stateAZ -2.341129 0.757558 -3.090 0.002017 **
## stateCA -0.346416 0.627994 -0.552 0.581247
## stateCO -1.875605 0.612311 -3.063 0.002209 **
## stateCT -3.512105 0.908410 -3.866 0.000113 ***
## stateDE -1.241373 1.280337 -0.970 0.332339
## stateFL -0.524613 0.564728 -0.929 0.352980
## stateGA -1.729956 0.559038 -3.095 0.001989 **
## stateIA -0.226581 0.611864 -0.370 0.711175
## stateID -3.284423 0.649272 -5.059 4.47e-07 ***
## stateIL -1.443436 0.610261 -2.365 0.018078 *
## stateIN -0.760248 0.628101 -1.210 0.226222
## stateKS -0.285623 0.603199 -0.474 0.635881
## stateKY -0.622675 0.599084 -1.039 0.298711
## stateLA 0.755878 0.610106 1.239 0.215467
## stateMA -1.649099 0.768886 -2.145 0.032048 *
## stateMD -1.068017 0.701122 -1.523 0.127788
## stateME 0.008856 0.752832 0.012 0.990615
## stateMI -1.840139 0.584397 -3.149 0.001655 **
## stateMN -0.317587 0.607083 -0.523 0.600917
## stateMO -1.012687 0.583810 -1.735 0.082909 .
## stateMS -0.277054 0.589548 -0.470 0.638430
## stateMT -2.395123 0.628366 -3.812 0.000141 ***
## stateNC -1.367791 0.589294 -2.321 0.020348 *
## stateND -0.761455 0.634527 -1.200 0.230219
## stateNE -0.125045 0.600444 -0.208 0.835045
## stateNH -0.535353 0.839357 -0.638 0.523643
## stateNJ -1.293646 0.717088 -1.804 0.071325 .
## stateNM -1.698613 0.645150 -2.633 0.008508 **
## stateNV -0.567833 0.746121 -0.761 0.446688
## stateNY -1.603223 0.623780 -2.570 0.010212 *
## stateOH -0.197501 0.623009 -0.317 0.751256
## stateOK -0.837695 0.578708 -1.448 0.147852
## stateOR -1.474484 0.675741 -2.182 0.029183 *
## statePA -1.808590 0.632927 -2.858 0.004299 **
## stateRI -3.093028 1.144164 -2.703 0.006903 **
## stateSC -1.803119 0.618006 -2.918 0.003553 **
## stateSD -1.507730 0.626636 -2.406 0.016184 *
## stateTN -1.522170 0.593992 -2.563 0.010436 *
## stateTX -1.036589 0.543045 -1.909 0.056375 .
## stateUT -2.066141 0.658967 -3.135 0.001732 **
## stateVA -1.413258 0.593433 -2.381 0.017303 *
## stateVT -1.198493 0.768860 -1.559 0.119149
## stateWA -1.211064 0.667535 -1.814 0.069740 .
## stateWI -0.613653 0.609219 -1.007 0.313881
## stateWV -0.357039 0.631932 -0.565 0.572118
## stateWY -2.485299 0.694834 -3.577 0.000353 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 1.985 on 3066 degrees of freedom
## (11 observations deleted due to missingness)
## Multiple R-squared: 0.5253, Adjusted R-squared: 0.5167
## F-statistic: 61.68 on 55 and 3066 DF, p-value: < 2.2e-16
X<-df%>%
select(
per_black_norm,
per_asian_norm,
per_elderly_norm,
per_noenglish_norm,
per_female_hh_with_kids_under6_norm,
per_rural_norm,
per_below_poverty_norm,
per_rent_norm,
per_no_carnorm,
per_college_or_higher_norm,
average_hh_norm,
per_lack_plumbing_norm,
per_mobile_home_norm,
air_quality_norm,
water_quality_norm,
built_quality_norm,
land_quality_norm,
impervious_surface_norm,
per_nursingnorm,
FEMA_total_norm,
number_research_institutions_norm,
employees_2001_norm)
ggpairs(X)
## Warning in ggally_statistic(data = data, mapping = mapping, na.rm = na.rm, :
## Removed 11 rows containing missing values
## Warning in ggally_statistic(data = data, mapping = mapping, na.rm = na.rm, :
## Removed 11 rows containing missing values
## Warning in ggally_statistic(data = data, mapping = mapping, na.rm = na.rm, :
## Removed 11 rows containing missing values
## Warning in ggally_statistic(data = data, mapping = mapping, na.rm = na.rm, :
## Removed 11 rows containing missing values
## Warning in ggally_statistic(data = data, mapping = mapping, na.rm = na.rm, :
## Removed 11 rows containing missing values
## Warning in ggally_statistic(data = data, mapping = mapping, na.rm = na.rm, :
## Removed 11 rows containing missing values
## Warning in ggally_statistic(data = data, mapping = mapping, na.rm = na.rm, :
## Removed 11 rows containing missing values
## Warning in ggally_statistic(data = data, mapping = mapping, na.rm = na.rm, :
## Removed 11 rows containing missing values
## Warning in ggally_statistic(data = data, mapping = mapping, na.rm = na.rm, :
## Removed 11 rows containing missing values
## Warning in ggally_statistic(data = data, mapping = mapping, na.rm = na.rm, :
## Removed 11 rows containing missing values
## Warning in ggally_statistic(data = data, mapping = mapping, na.rm = na.rm, :
## Removed 11 rows containing missing values
## Warning in ggally_statistic(data = data, mapping = mapping, na.rm = na.rm, :
## Removed 11 rows containing missing values
## Warning in ggally_statistic(data = data, mapping = mapping, na.rm = na.rm, :
## Removed 11 rows containing missing values
## Warning in ggally_statistic(data = data, mapping = mapping, na.rm = na.rm, :
## Removed 11 rows containing missing values
## Warning in ggally_statistic(data = data, mapping = mapping, na.rm = na.rm, :
## Removed 11 rows containing missing values
## Warning in ggally_statistic(data = data, mapping = mapping, na.rm = na.rm, :
## Removed 11 rows containing missing values
## Warning in ggally_statistic(data = data, mapping = mapping, na.rm = na.rm, :
## Removed 11 rows containing missing values
## Warning in ggally_statistic(data = data, mapping = mapping, na.rm = na.rm, :
## Removed 11 rows containing missing values
## Warning in ggally_statistic(data = data, mapping = mapping, na.rm = na.rm, :
## Removed 11 rows containing missing values
## Warning in ggally_statistic(data = data, mapping = mapping, na.rm = na.rm, :
## Removed 11 rows containing missing values
## Warning in ggally_statistic(data = data, mapping = mapping, na.rm = na.rm, :
## Removed 11 rows containing missing values
## Warning in ggally_statistic(data = data, mapping = mapping, na.rm = na.rm, :
## Removed 11 rows containing missing values
## Warning in ggally_statistic(data = data, mapping = mapping, na.rm = na.rm, :
## Removed 11 rows containing missing values
## Warning in ggally_statistic(data = data, mapping = mapping, na.rm = na.rm, :
## Removed 11 rows containing missing values
## Warning in ggally_statistic(data = data, mapping = mapping, na.rm = na.rm, :
## Removed 11 rows containing missing values
## Warning in ggally_statistic(data = data, mapping = mapping, na.rm = na.rm, :
## Removed 11 rows containing missing values
## Warning in ggally_statistic(data = data, mapping = mapping, na.rm = na.rm, :
## Removed 11 rows containing missing values
## Warning in ggally_statistic(data = data, mapping = mapping, na.rm = na.rm, :
## Removed 11 rows containing missing values
## Warning in ggally_statistic(data = data, mapping = mapping, na.rm = na.rm, :
## Removed 11 rows containing missing values
## Warning in ggally_statistic(data = data, mapping = mapping, na.rm = na.rm, :
## Removed 11 rows containing missing values
## Warning in ggally_statistic(data = data, mapping = mapping, na.rm = na.rm, :
## Removed 11 rows containing missing values
## Warning in ggally_statistic(data = data, mapping = mapping, na.rm = na.rm, :
## Removed 11 rows containing missing values
## Warning in ggally_statistic(data = data, mapping = mapping, na.rm = na.rm, :
## Removed 11 rows containing missing values
## Warning in ggally_statistic(data = data, mapping = mapping, na.rm = na.rm, :
## Removed 11 rows containing missing values
## Warning in ggally_statistic(data = data, mapping = mapping, na.rm = na.rm, :
## Removed 11 rows containing missing values
## Warning in ggally_statistic(data = data, mapping = mapping, na.rm = na.rm, :
## Removed 11 rows containing missing values
## Warning in ggally_statistic(data = data, mapping = mapping, na.rm = na.rm, :
## Removed 11 rows containing missing values
## Warning in ggally_statistic(data = data, mapping = mapping, na.rm = na.rm, :
## Removed 11 rows containing missing values
## Warning in ggally_statistic(data = data, mapping = mapping, na.rm = na.rm, :
## Removed 11 rows containing missing values
## Warning in ggally_statistic(data = data, mapping = mapping, na.rm = na.rm, :
## Removed 11 rows containing missing values
## Warning in ggally_statistic(data = data, mapping = mapping, na.rm = na.rm, :
## Removed 11 rows containing missing values
## Warning in ggally_statistic(data = data, mapping = mapping, na.rm = na.rm, :
## Removed 11 rows containing missing values
## Warning in ggally_statistic(data = data, mapping = mapping, na.rm = na.rm, :
## Removed 11 rows containing missing values
## Warning in ggally_statistic(data = data, mapping = mapping, na.rm = na.rm, :
## Removed 11 rows containing missing values
## Warning in ggally_statistic(data = data, mapping = mapping, na.rm = na.rm, :
## Removed 11 rows containing missing values
## Warning in ggally_statistic(data = data, mapping = mapping, na.rm = na.rm, :
## Removed 11 rows containing missing values
## Warning in ggally_statistic(data = data, mapping = mapping, na.rm = na.rm, :
## Removed 11 rows containing missing values
## Warning in ggally_statistic(data = data, mapping = mapping, na.rm = na.rm, :
## Removed 11 rows containing missing values
## Warning in ggally_statistic(data = data, mapping = mapping, na.rm = na.rm, :
## Removed 11 rows containing missing values
## Warning in ggally_statistic(data = data, mapping = mapping, na.rm = na.rm, :
## Removed 11 rows containing missing values
## Warning in ggally_statistic(data = data, mapping = mapping, na.rm = na.rm, :
## Removed 11 rows containing missing values
## Warning in ggally_statistic(data = data, mapping = mapping, na.rm = na.rm, :
## Removed 11 rows containing missing values
## Warning in ggally_statistic(data = data, mapping = mapping, na.rm = na.rm, :
## Removed 11 rows containing missing values
## Warning in ggally_statistic(data = data, mapping = mapping, na.rm = na.rm, :
## Removed 11 rows containing missing values
## Warning in ggally_statistic(data = data, mapping = mapping, na.rm = na.rm, :
## Removed 11 rows containing missing values
## Warning in ggally_statistic(data = data, mapping = mapping, na.rm = na.rm, :
## Removed 11 rows containing missing values
## Warning in ggally_statistic(data = data, mapping = mapping, na.rm = na.rm, :
## Removed 11 rows containing missing values
## Warning in ggally_statistic(data = data, mapping = mapping, na.rm = na.rm, :
## Removed 11 rows containing missing values
## Warning in ggally_statistic(data = data, mapping = mapping, na.rm = na.rm, :
## Removed 11 rows containing missing values
## Warning in ggally_statistic(data = data, mapping = mapping, na.rm = na.rm, :
## Removed 11 rows containing missing values
## Warning in ggally_statistic(data = data, mapping = mapping, na.rm = na.rm, :
## Removed 11 rows containing missing values
## Warning in ggally_statistic(data = data, mapping = mapping, na.rm = na.rm, :
## Removed 11 rows containing missing values
## Warning in ggally_statistic(data = data, mapping = mapping, na.rm = na.rm, :
## Removed 11 rows containing missing values
## Warning in ggally_statistic(data = data, mapping = mapping, na.rm = na.rm, :
## Removed 11 rows containing missing values
## Warning in ggally_statistic(data = data, mapping = mapping, na.rm = na.rm, :
## Removed 11 rows containing missing values
## Warning: Removed 11 rows containing missing values (`geom_point()`).
## Removed 11 rows containing missing values (`geom_point()`).
## Removed 11 rows containing missing values (`geom_point()`).
## Removed 11 rows containing missing values (`geom_point()`).
## Removed 11 rows containing missing values (`geom_point()`).
## Removed 11 rows containing missing values (`geom_point()`).
## Removed 11 rows containing missing values (`geom_point()`).
## Removed 11 rows containing missing values (`geom_point()`).
## Removed 11 rows containing missing values (`geom_point()`).
## Removed 11 rows containing missing values (`geom_point()`).
## Removed 11 rows containing missing values (`geom_point()`).
## Removed 11 rows containing missing values (`geom_point()`).
## Removed 11 rows containing missing values (`geom_point()`).
## Warning: Removed 11 rows containing non-finite values (`stat_density()`).
## Warning in ggally_statistic(data = data, mapping = mapping, na.rm = na.rm, :
## Removed 11 rows containing missing values
## Warning in ggally_statistic(data = data, mapping = mapping, na.rm = na.rm, :
## Removed 11 rows containing missing values
## Warning in ggally_statistic(data = data, mapping = mapping, na.rm = na.rm, :
## Removed 11 rows containing missing values
## Warning in ggally_statistic(data = data, mapping = mapping, na.rm = na.rm, :
## Removed 11 rows containing missing values
## Warning in ggally_statistic(data = data, mapping = mapping, na.rm = na.rm, :
## Removed 11 rows containing missing values
## Warning in ggally_statistic(data = data, mapping = mapping, na.rm = na.rm, :
## Removed 11 rows containing missing values
## Warning in ggally_statistic(data = data, mapping = mapping, na.rm = na.rm, :
## Removed 11 rows containing missing values
## Warning in ggally_statistic(data = data, mapping = mapping, na.rm = na.rm, :
## Removed 11 rows containing missing values
## Warning: Removed 11 rows containing missing values (`geom_point()`).
## Removed 11 rows containing missing values (`geom_point()`).
## Removed 11 rows containing missing values (`geom_point()`).
## Removed 11 rows containing missing values (`geom_point()`).
## Removed 11 rows containing missing values (`geom_point()`).
## Removed 11 rows containing missing values (`geom_point()`).
## Removed 11 rows containing missing values (`geom_point()`).
## Removed 11 rows containing missing values (`geom_point()`).
## Removed 11 rows containing missing values (`geom_point()`).
## Removed 11 rows containing missing values (`geom_point()`).
## Removed 11 rows containing missing values (`geom_point()`).
## Removed 11 rows containing missing values (`geom_point()`).
## Removed 11 rows containing missing values (`geom_point()`).
## Removed 11 rows containing missing values (`geom_point()`).
## Warning: Removed 11 rows containing non-finite values (`stat_density()`).
## Warning in ggally_statistic(data = data, mapping = mapping, na.rm = na.rm, :
## Removed 11 rows containing missing values
## Warning in ggally_statistic(data = data, mapping = mapping, na.rm = na.rm, :
## Removed 11 rows containing missing values
## Warning in ggally_statistic(data = data, mapping = mapping, na.rm = na.rm, :
## Removed 11 rows containing missing values
## Warning in ggally_statistic(data = data, mapping = mapping, na.rm = na.rm, :
## Removed 11 rows containing missing values
## Warning in ggally_statistic(data = data, mapping = mapping, na.rm = na.rm, :
## Removed 11 rows containing missing values
## Warning in ggally_statistic(data = data, mapping = mapping, na.rm = na.rm, :
## Removed 11 rows containing missing values
## Warning in ggally_statistic(data = data, mapping = mapping, na.rm = na.rm, :
## Removed 11 rows containing missing values
## Warning: Removed 11 rows containing missing values (`geom_point()`).
## Removed 11 rows containing missing values (`geom_point()`).
## Removed 11 rows containing missing values (`geom_point()`).
## Removed 11 rows containing missing values (`geom_point()`).
## Removed 11 rows containing missing values (`geom_point()`).
## Removed 11 rows containing missing values (`geom_point()`).
## Removed 11 rows containing missing values (`geom_point()`).
## Removed 11 rows containing missing values (`geom_point()`).
## Removed 11 rows containing missing values (`geom_point()`).
## Removed 11 rows containing missing values (`geom_point()`).
## Removed 11 rows containing missing values (`geom_point()`).
## Removed 11 rows containing missing values (`geom_point()`).
## Removed 11 rows containing missing values (`geom_point()`).
## Removed 11 rows containing missing values (`geom_point()`).
## Removed 11 rows containing missing values (`geom_point()`).
## Warning: Removed 11 rows containing non-finite values (`stat_density()`).
## Warning in ggally_statistic(data = data, mapping = mapping, na.rm = na.rm, :
## Removed 11 rows containing missing values
## Warning in ggally_statistic(data = data, mapping = mapping, na.rm = na.rm, :
## Removed 11 rows containing missing values
## Warning in ggally_statistic(data = data, mapping = mapping, na.rm = na.rm, :
## Removed 11 rows containing missing values
## Warning in ggally_statistic(data = data, mapping = mapping, na.rm = na.rm, :
## Removed 11 rows containing missing values
## Warning in ggally_statistic(data = data, mapping = mapping, na.rm = na.rm, :
## Removed 11 rows containing missing values
## Warning in ggally_statistic(data = data, mapping = mapping, na.rm = na.rm, :
## Removed 11 rows containing missing values
## Warning: Removed 11 rows containing missing values (`geom_point()`).
## Removed 11 rows containing missing values (`geom_point()`).
## Removed 11 rows containing missing values (`geom_point()`).
## Removed 11 rows containing missing values (`geom_point()`).
## Removed 11 rows containing missing values (`geom_point()`).
## Removed 11 rows containing missing values (`geom_point()`).
## Removed 11 rows containing missing values (`geom_point()`).
## Removed 11 rows containing missing values (`geom_point()`).
## Removed 11 rows containing missing values (`geom_point()`).
## Removed 11 rows containing missing values (`geom_point()`).
## Removed 11 rows containing missing values (`geom_point()`).
## Removed 11 rows containing missing values (`geom_point()`).
## Removed 11 rows containing missing values (`geom_point()`).
## Removed 11 rows containing missing values (`geom_point()`).
## Removed 11 rows containing missing values (`geom_point()`).
## Removed 11 rows containing missing values (`geom_point()`).
## Warning: Removed 11 rows containing non-finite values (`stat_density()`).
## Warning in ggally_statistic(data = data, mapping = mapping, na.rm = na.rm, :
## Removed 11 rows containing missing values
## Warning in ggally_statistic(data = data, mapping = mapping, na.rm = na.rm, :
## Removed 11 rows containing missing values
## Warning in ggally_statistic(data = data, mapping = mapping, na.rm = na.rm, :
## Removed 11 rows containing missing values
## Warning in ggally_statistic(data = data, mapping = mapping, na.rm = na.rm, :
## Removed 11 rows containing missing values
## Warning in ggally_statistic(data = data, mapping = mapping, na.rm = na.rm, :
## Removed 11 rows containing missing values
## Warning: Removed 11 rows containing missing values (`geom_point()`).
## Removed 11 rows containing missing values (`geom_point()`).
## Removed 11 rows containing missing values (`geom_point()`).
## Removed 11 rows containing missing values (`geom_point()`).
## Removed 11 rows containing missing values (`geom_point()`).
## Removed 11 rows containing missing values (`geom_point()`).
## Removed 11 rows containing missing values (`geom_point()`).
## Removed 11 rows containing missing values (`geom_point()`).
## Removed 11 rows containing missing values (`geom_point()`).
## Removed 11 rows containing missing values (`geom_point()`).
## Removed 11 rows containing missing values (`geom_point()`).
## Removed 11 rows containing missing values (`geom_point()`).
## Removed 11 rows containing missing values (`geom_point()`).
## Removed 11 rows containing missing values (`geom_point()`).
## Removed 11 rows containing missing values (`geom_point()`).
## Removed 11 rows containing missing values (`geom_point()`).
## Removed 11 rows containing missing values (`geom_point()`).
## Warning: Removed 11 rows containing non-finite values (`stat_density()`).
## Warning in ggally_statistic(data = data, mapping = mapping, na.rm = na.rm, :
## Removed 11 rows containing missing values
## Warning in ggally_statistic(data = data, mapping = mapping, na.rm = na.rm, :
## Removed 11 rows containing missing values
## Warning in ggally_statistic(data = data, mapping = mapping, na.rm = na.rm, :
## Removed 11 rows containing missing values
## Warning in ggally_statistic(data = data, mapping = mapping, na.rm = na.rm, :
## Removed 11 rows containing missing values
## Warning: Removed 11 rows containing missing values (`geom_point()`).
## Removed 11 rows containing missing values (`geom_point()`).
## Removed 11 rows containing missing values (`geom_point()`).
## Removed 11 rows containing missing values (`geom_point()`).
## Removed 11 rows containing missing values (`geom_point()`).
## Removed 11 rows containing missing values (`geom_point()`).
## Removed 11 rows containing missing values (`geom_point()`).
## Removed 11 rows containing missing values (`geom_point()`).
## Removed 11 rows containing missing values (`geom_point()`).
## Removed 11 rows containing missing values (`geom_point()`).
## Removed 11 rows containing missing values (`geom_point()`).
## Removed 11 rows containing missing values (`geom_point()`).
## Removed 11 rows containing missing values (`geom_point()`).
## Removed 11 rows containing missing values (`geom_point()`).
## Removed 11 rows containing missing values (`geom_point()`).
## Removed 11 rows containing missing values (`geom_point()`).
## Removed 11 rows containing missing values (`geom_point()`).
## Removed 11 rows containing missing values (`geom_point()`).
## Removed 11 rows containing missing values (`geom_point()`).
## Removed 11 rows containing missing values (`geom_point()`).
model_dmg <- lm(prop_dmg_log~ (per_black_norm+
per_asian_norm+
per_elderly_norm+
per_noenglish_norm+
per_female_hh_with_kids_under6_norm+
per_rural_norm)+
(per_nursingnorm)+
(per_below_poverty_norm+
per_rent_norm+
per_no_carnorm+
per_college_or_higher_norm+
average_hh_norm+
per_lack_plumbing_norm+
per_mobile_home_norm)
+
(FEMA_total_norm+
number_research_institutions_norm+
employees_2001_norm)
+
(air_quality_norm+
water_quality_norm+
built_quality_norm+
land_quality_norm+
impervious_surface_norm )+
log_pop_2000+numb_haz_log+state,data=df, na.rm=TRUE)
## Warning: In lm.fit(x, y, offset = offset, singular.ok = singular.ok, ...) :
## extra argument 'na.rm' will be disregarded
summary(model_dmg)
##
## Call:
## lm(formula = prop_dmg_log ~ (per_black_norm + per_asian_norm +
## per_elderly_norm + per_noenglish_norm + per_female_hh_with_kids_under6_norm +
## per_rural_norm) + (per_nursingnorm) + (per_below_poverty_norm +
## per_rent_norm + per_no_carnorm + per_college_or_higher_norm +
## average_hh_norm + per_lack_plumbing_norm + per_mobile_home_norm) +
## (FEMA_total_norm + number_research_institutions_norm + employees_2001_norm) +
## (air_quality_norm + water_quality_norm + built_quality_norm +
## land_quality_norm + impervious_surface_norm) + log_pop_2000 +
## numb_haz_log + state, data = df, na.rm = TRUE)
##
## Residuals:
## Min 1Q Median 3Q Max
## -13.9117 -1.0234 0.0028 1.0649 9.1663
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 6.133575 1.100001 5.576 2.68e-08 ***
## per_black_norm -0.046819 0.067999 -0.689 0.491173
## per_asian_norm -0.014160 0.071998 -0.197 0.844101
## per_elderly_norm 0.150988 0.082202 1.837 0.066338 .
## per_noenglish_norm -0.186799 0.293024 -0.637 0.523857
## per_female_hh_with_kids_under6_norm 0.118805 0.073310 1.621 0.105210
## per_rural_norm -0.143811 0.078516 -1.832 0.067107 .
## per_nursingnorm 0.022557 0.046965 0.480 0.631058
## per_below_poverty_norm 0.132165 0.096568 1.369 0.171219
## per_rent_norm -0.271786 0.072752 -3.736 0.000191 ***
## per_no_carnorm -0.127852 0.083383 -1.533 0.125303
## per_college_or_higher_norm 0.097757 0.065406 1.495 0.135117
## average_hh_norm -0.001195 0.081989 -0.015 0.988375
## per_lack_plumbing_norm -0.034500 0.059857 -0.576 0.564402
## per_mobile_home_norm 0.068934 0.068568 1.005 0.314817
## FEMA_total_norm 0.288967 0.037395 7.727 1.48e-14 ***
## number_research_institutions_norm 0.081085 0.048363 1.677 0.093726 .
## employees_2001_norm -0.131824 0.054504 -2.419 0.015639 *
## air_quality_norm -0.001464 0.105738 -0.014 0.988957
## water_quality_norm -0.099260 0.062269 -1.594 0.111029
## built_quality_norm -0.027230 0.052658 -0.517 0.605116
## land_quality_norm -0.055001 0.058040 -0.948 0.343381
## impervious_surface_norm 0.054222 0.058554 0.926 0.354509
## log_pop_2000 0.598127 0.074553 8.023 1.46e-15 ***
## numb_haz_log 3.216028 0.101818 31.586 < 2e-16 ***
## stateAL -3.778256 0.792980 -4.765 1.98e-06 ***
## stateAR -2.410592 0.769724 -3.132 0.001754 **
## stateAZ -4.019894 0.909566 -4.420 1.02e-05 ***
## stateCA -1.634443 0.786012 -2.079 0.037663 *
## stateCO -3.456676 0.777166 -4.448 8.99e-06 ***
## stateCT -5.182676 1.020742 -5.077 4.06e-07 ***
## stateDE -3.273824 1.366629 -2.396 0.016656 *
## stateFL -2.774593 0.784352 -3.537 0.000410 ***
## stateGA -3.419064 0.759902 -4.499 7.07e-06 ***
## stateIA -2.072677 0.778442 -2.663 0.007795 **
## stateID -5.006705 0.813743 -6.153 8.61e-10 ***
## stateIL -3.300871 0.782859 -4.216 2.55e-05 ***
## stateIN -2.564363 0.791777 -3.239 0.001213 **
## stateKS -2.109034 0.777087 -2.714 0.006684 **
## stateKY -2.418756 0.785049 -3.081 0.002081 **
## stateLA -1.330125 0.805633 -1.651 0.098835 .
## stateMA -3.448308 0.905297 -3.809 0.000142 ***
## stateMD -2.727861 0.845809 -3.225 0.001272 **
## stateME -1.718621 0.883373 -1.946 0.051804 .
## stateMI -3.708460 0.756064 -4.905 9.83e-07 ***
## stateMN -2.202305 0.766574 -2.873 0.004095 **
## stateMO -2.813579 0.763928 -3.683 0.000234 ***
## stateMS -2.143115 0.796772 -2.690 0.007190 **
## stateMT -4.167146 0.801879 -5.197 2.16e-07 ***
## stateNC -3.110131 0.785152 -3.961 7.63e-05 ***
## stateND -2.634533 0.803478 -3.279 0.001054 **
## stateNE -1.898465 0.778565 -2.438 0.014809 *
## stateNH -2.171100 0.959492 -2.263 0.023721 *
## stateNJ -2.935751 0.854897 -3.434 0.000603 ***
## stateNM -3.683843 0.822705 -4.478 7.82e-06 ***
## stateNV -2.184398 0.900024 -2.427 0.015280 *
## stateNY -3.128163 0.777010 -4.026 5.81e-05 ***
## stateOH -1.980036 0.791220 -2.503 0.012384 *
## stateOK -2.668082 0.765587 -3.485 0.000499 ***
## stateOR -3.174767 0.840079 -3.779 0.000160 ***
## statePA -3.538489 0.794177 -4.456 8.67e-06 ***
## stateRI -5.167139 1.242857 -4.157 3.31e-05 ***
## stateSC -3.579631 0.814992 -4.392 1.16e-05 ***
## stateSD -3.277706 0.802607 -4.084 4.54e-05 ***
## stateTN -3.285390 0.781226 -4.205 2.68e-05 ***
## stateTX -2.793664 0.739818 -3.776 0.000162 ***
## stateUT -3.799232 0.816689 -4.652 3.43e-06 ***
## stateVA -3.181199 0.773707 -4.112 4.03e-05 ***
## stateVT -2.844917 0.896528 -3.173 0.001522 **
## stateWA -2.833553 0.821982 -3.447 0.000574 ***
## stateWI -2.317237 0.767123 -3.021 0.002543 **
## stateWV -2.243051 0.805734 -2.784 0.005405 **
## stateWY -4.194137 0.848876 -4.941 8.20e-07 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 1.959 on 3049 degrees of freedom
## (11 observations deleted due to missingness)
## Multiple R-squared: 0.5403, Adjusted R-squared: 0.5295
## F-statistic: 49.78 on 72 and 3049 DF, p-value: < 2.2e-16
Social Dimension and Causality